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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mental
    -0.07
     budouc
    -0.07
     silah
    -0.06
    感情
    -0.06
     signal
    -0.06
     paypal
    -0.06
     '?'
    -0.06
     bitten
    -0.06
    Cos
    -0.06
     хотел
    -0.06
    POSITIVE LOGITS
    CATEGORY
    0.07
     stickers
    0.06
     decad
    0.06
     Jacob
    0.06
    -Disposition
    0.06
    νοντας
    0.06
     hashCode
    0.06
    .getFile
    0.06
    styl
    0.06
     RouteServiceProvider
    0.06
    Act Density 0.341%

    No Known Activations