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

    Neuronpedia

    INDEX
    Explanations

    attr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تق
    -0.09
    崩溃
    -0.08
    (de
    -0.08
     म
    -0.08
     owed
    -0.08
    渡
    -0.07
    一瓶
    -0.07
    #create
    -0.07
    /code
    -0.07
     weighs
    -0.07
    POSITIVE LOGITS
    ائح
    0.08
     fashion
    0.08
    ligt
    0.07
     предпоч
    0.07
    atif
    0.07
    绋
    0.07
    fstream
    0.07
    ꇴ
    0.07
    StyleSheet
    0.06
    .direction
    0.06
    Act Density 0.001%

    No Known Activations