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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     указ
    -0.07
    愛
    -0.07
     burden
    -0.07
     sophomore
    -0.06
    عت
    -0.06
     UNU
    -0.06
    _FMT
    -0.06
     brochure
    -0.06
    手机号
    -0.06
     хви
    -0.06
    POSITIVE LOGITS
    iclass
    0.06
    .Security
    0.06
     محمد
    0.06
    PyObject
    0.06
    兼
    0.06
    �
    0.06
     poems
    0.06
    icher
    0.06
     temper
    0.06
    _holder
    0.06
    Act Density 0.020%

    No Known Activations