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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    night
    -0.07
    .getInstance
    -0.07
    واز
    -0.07
    _Player
    -0.06
    ServiceProvider
    -0.06
     Stout
    -0.06
    IDTH
    -0.06
    ods
    -0.06
    اءة
    -0.06
    lararası
    -0.06
    POSITIVE LOGITS
    roman
    0.06
     arbit
    0.06
    Checked
    0.06
    Lbl
    0.06
    itle
    0.06
     Stephan
    0.06
     ontvang
    0.06
    込み
    0.06
     prosec
    0.06
     reporting
    0.06
    Act Density 0.003%

    No Known Activations