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

    Neuronpedia

    INDEX
    Explanations

    Give

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Top
    -0.07
    🌺
    -0.07
    榮
    -0.07
    菟
    -0.07
     Ży
    -0.06
    .addButton
    -0.06
    _ROT
    -0.06
     sí
    -0.06
     Roof
    -0.06
    לים
    -0.06
    POSITIVE LOGITS
    Std
    0.07
     nested
    0.07
     constituents
    0.06
    стой
    0.06
    vik
    0.06
    sha
    0.06
     cb
    0.06
    охран
    0.06
    份额
    0.06
    영상
    0.06
    Act Density 0.001%

    No Known Activations