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

    Neuronpedia

    INDEX
    Explanations

    teamwork

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rot
    -0.07
     Gibson
    -0.07
    /@
    -0.07
     slope
    -0.06
     Çocuk
    -0.06
    AWN
    -0.06
    _dic
    -0.06
    ut
    -0.06
    ade
    -0.06
    Norm
    -0.06
    POSITIVE LOGITS
    robat
    0.07
    .aggregate
    0.06
     Legislation
    0.06
    Encoding
    0.06
    RoleId
    0.06
    ходим
    0.06
    鲁
    0.06
     가족
    0.06
    paration
    0.06
    -confidence
    0.06
    Act Density 0.233%

    No Known Activations