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

    Neuronpedia

    INDEX
    Explanations

    JSON syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "]->
    -0.07
     مفهوم
    -0.07
     آثار
    -0.07
     Mun
    -0.06
    .just
    -0.06
    _hand
    -0.06
    .find
    -0.06
    ностей
    -0.06
    缩
    -0.06
     Jenner
    -0.06
    POSITIVE LOGITS
    parallel
    0.07
    -buy
    0.07
    σφα
    0.06
    block
    0.06
    及び
    0.06
     chill
    0.06
    —the
    0.06
    ghi
    0.06
     стали
    0.06
    、その
    0.06
    Act Density 0.049%

    No Known Activations