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

    Neuronpedia

    INDEX
    Explanations

    URLs and social media links

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

    URLs or domains

    np_acts-logits-general · gemini-2.0-flash

    URLs and public works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unknownFields
    -0.92
     Roskov
    -0.85
    parsedMessage
    -0.84
    awtextra
    -0.79
    ConstraintMaker
    -0.75
     beginnetje
    -0.73
    ValueStyle
    -0.72
     Normdatei
    -0.71
     nettsted
    -0.71
    LookAnd
    -0.71
    POSITIVE LOGITS
     ac
    0.50
    auth
    0.48
    giu
    0.47
     mat
    0.47
    username
    0.45
     masked
    0.44
    ️
    0.43
     @
    0.43
    issau
    0.43
     Suche
    0.43
    Act Density 0.091%

    No Known Activations