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

    Neuronpedia

    INDEX
    Explanations

    expressions of seeking help or assistance with problems

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

    first-person statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.69
     Chwiliwch
    -0.66
    MessageTagHelper
    -0.60
    Geplaatst
    -0.57
     Numerade
    -0.56
    LookAnd
    -0.52
    apimachinery
    -0.50
     bezeichneter
    -0.49
     Roskov
    -0.48
    تقاوى
    -0.47
    POSITIVE LOGITS
     weeds
    0.53
     Glee
    0.52
     RDA
    0.50
     Alton
    0.48
     Lexus
    0.47
    𖣘
    0.47
     frustrations
    0.47
     Anastasia
    0.47
     GED
    0.47
    lorn
    0.46
    Act Density 0.049%

    No Known Activations