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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or expressions of agreement

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

    Follows "yes" or "Yes"

    np_acts-logits-general · gemini-2.0-flash

    affirmative responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.81
    +#+
    -0.77
    MLLoader
    -0.76
    يكب
    -0.70
     Roskov
    -0.68
    RTEE
    -0.68
    WireFormatLite
    -0.68
    RenderAtEndOf
    -0.67
    逅
    -0.67
    Datuak
    -0.66
    POSITIVE LOGITS
     indeed
    0.97
    sir
    0.89
    ssss
    0.80
    Indeed
    0.80
     Indeed
    0.78
    indeed
    0.74
     sir
    0.73
    sssss
    0.73
    sss
    0.72
    ssssssss
    0.71
    Act Density 0.052%

    No Known Activations