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

    Neuronpedia

    INDEX
    Explanations

    Series

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تمامی
    -0.07
     embassy
    -0.07
     jež
    -0.06
    Detail
    -0.06
     tránh
    -0.06
     fruity
    -0.06
    íš
    -0.06
     миров
    -0.06
     Beverage
    -0.06
    Bước
    -0.06
    POSITIVE LOGITS
    /bower
    0.07
    (ALOAD
    0.07
    Annotation
    0.07
    [k
    0.06
    .getSession
    0.06
    <char
    0.06
     Emin
    0.06
    ای
    0.06
    ��
    0.06
    /storage
    0.06
    Act Density 0.015%

    No Known Activations