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

    Neuronpedia

    INDEX
    Explanations

    pandas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abortion
    -0.07
     Arc
    -0.06
     papers
    -0.06
    _mac
    -0.06
    _mex
    -0.06
     Evan
    -0.06
    borg
    -0.06
     아주
    -0.06
     beetle
    -0.06
    -version
    -0.06
    POSITIVE LOGITS
    (Index
    0.08
    _kelas
    0.07
     Gupta
    0.07
     صلى
    0.07
     نف
    0.06
    ději
    0.06
    .endTime
    0.06
    undy
    0.06
    imilar
    0.06
    едера
    0.06
    Act Density 0.006%

    No Known Activations