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

    Neuronpedia

    INDEX
    Explanations

    phrases in dialogue indicating confusion or surprise

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TextInputType
    -0.73
     للمعارف
    -0.69
     وتسجيلات
    -0.60
    extAlignment
    -0.52
     pay
    -0.51
     GSM
    -0.51
    IDENTAL
    -0.51
    vements
    -0.50
    doe
    -0.49
    Swiper
    -0.49
    POSITIVE LOGITS
    InitStruct
    0.74
    GeneratedCode
    0.69
    เหร
    0.52
    ?"
    0.51
    ?!
    0.51
     ?!
    0.50
    CppMethod
    0.50
    imply
    0.49
    ?!?
    0.48
    maintained
    0.48
    Act Density 0.027%

    No Known Activations