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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ragazze
    -0.08
     presente
    -0.07
     주
    -0.06
     tỉ
    -0.06
     disse
    -0.06
    照片
    -0.06
    ном
    -0.06
    _x
    -0.06
     monsters
    -0.06
     zd
    -0.06
    POSITIVE LOGITS
     withholding
    0.07
    ’l
    0.07
    ्मक
    0.06
     lj
    0.06
    asmine
    0.06
    utters
    0.06
     Tri
    0.06
     gathering
    0.06
     distributes
    0.06
    entic
    0.06
    Act Density 0.000%

    No Known Activations