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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narciss
    -0.07
     dismissed
    -0.06
     creativity
    -0.06
    ��
    -0.06
     scrolled
    -0.06
    _File
    -0.06
    ulsion
    -0.06
    ANTLR
    -0.06
    antly
    -0.06
     mirrored
    -0.06
    POSITIVE LOGITS
    ,q
    0.07
    enuine
    0.07
    ные
    0.06
     فت
    0.06
    holder
    0.06
    атор
    0.06
    getItem
    0.06
     atoms
    0.06
    ,True
    0.06
     vouchers
    0.06
    Act Density 0.020%

    No Known Activations