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

    Neuronpedia

    INDEX
    Explanations

    instances of scoring or performance metrics in competitive contexts

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

    following pronouns

    np_acts-logits-general · gemini-2.0-flash

    reflexive pronouns or plurals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.51
     للمعارف
    -0.47
    tagHelperRunner
    -0.45
    PMailer
    -0.39
    या
    -0.38
     mergeFrom
    -0.37
    ModelAttribute
    -0.36
     المعيارى
    -0.36
     autorytatywna
    -0.35
     CiNii
    -0.35
    POSITIVE LOGITS
    themselves
    0.69
     themselves
    0.62
     ujednoznacz
    0.52
     disambiguazione
    0.49
     Constitucional
    0.48
     SEDS
    0.47
     cherchés
    0.47
     jotka
    0.47
     yourselves
    0.47
     sisters
    0.46
    Act Density 1.585%

    No Known Activations