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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Not
    -0.06
     iframe
    -0.06
    аф
    -0.06
     Walker
    -0.06
     instinct
    -0.06
     August
    -0.06
    rection
    -0.06
    添加
    -0.06
    .Mode
    -0.06
    ogenic
    -0.06
    POSITIVE LOGITS
    cov
    0.07
     Mojo
    0.07
     brew
    0.07
    _hpp
    0.06
     Mavericks
    0.06
    announce
    0.06
     admir
    0.06
     meer
    0.06
    mayacak
    0.06
    /****************
    0.06
    Act Density 0.002%

    No Known Activations