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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Democrats
    -0.07
    าท
    -0.06
     bulb
    -0.06
     vật
    -0.06
    ulis
    -0.06
    ��
    -0.06
    rapped
    -0.06
     считается
    -0.06
     μπορεί
    -0.06
    obia
    -0.06
    POSITIVE LOGITS
     goofy
    0.07
     مك
    0.07
     ن
    0.07
    .Key
    0.07
     scars
    0.07
    �
    0.06
    //@
    0.06
    금
    0.06
     SZ
    0.06
     Surv
    0.06
    Act Density 0.008%

    No Known Activations