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

    Neuronpedia

    INDEX
    Explanations

    neuropsychology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pr
    -0.07
    脫
    -0.07
    考試
    -0.07
    prov
    -0.06
     [,
    -0.06
    ��
    -0.06
     crack
    -0.06
    �
    -0.06
    ýt
    -0.06
    渡
    -0.06
    POSITIVE LOGITS
    BagConstraints
    0.07
     banging
    0.07
    -all
    0.07
    getWindow
    0.07
    퐁
    0.07
     getArguments
    0.07
    뭏
    0.07
    饮用
    0.06
    Mix
    0.06
    errer
    0.06
    Act Density 0.034%

    No Known Activations