Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    patterns related to messages or error notifications in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by numbers or other characters

    np_acts-logits-general · gemini-2.0-flash

    localization strings and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.84
     StringTokenizer
    -0.80
    IntoConstraints
    -0.78
    FailureListener
    -0.78
    oredCriteria
    -0.77
    ьаж
    -0.76
     Insee
    -0.75
    windowFixed
    -0.75
    GEBURTSDATUM
    -0.74
    kháu
    -0.73
    POSITIVE LOGITS
    translation
    1.71
     translation
    0.82
     Translation
    0.77
    Translation
    0.75
     translations
    0.63
    TRANSL
    0.60
    translated
    0.54
    translations
    0.54
     Translations
    0.51
     TRANSLATION
    0.51
    Act Density 0.005%

    No Known Activations