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

    Neuronpedia

    INDEX
    Explanations

    punctuation and emoticons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Berger
    -0.07
    _Project
    -0.06
    -route
    -0.06
     flurry
    -0.06
     masses
    -0.06
    ーレ
    -0.06
    iage
    -0.06
    ursos
    -0.06
    708
    -0.06
     też
    -0.06
    POSITIVE LOGITS
     kad
    0.07
     kre
    0.06
     різні
    0.06
     مرد
    0.06
     querying
    0.06
    %</
    0.06
     Yesterday
    0.06
    MeasureSpec
    0.06
    ()=="
    0.06
    .builder
    0.06
    Act Density 0.029%

    No Known Activations