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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bbene
    -0.48
    soever
    -0.44
    הח
    -0.43
    avons
    -0.43
    føl
    -0.41
    ia
    -0.40
    ian
    -0.40
     Estudi
    -0.40
     overwritten
    -0.39
     stră
    -0.39
    POSITIVE LOGITS
     ostavi
    0.75
     ویکی‌پدیا
    0.74
    rawDesc
    0.70
    ArgsConstructor
    0.68
     مشين
    0.66
     الاطلاع
    0.63
    öglichkeiten
    0.61
    xase
    0.61
     viewDidLoad
    0.60
     autorytatywna
    0.60
    Act Density 0.075%

    No Known Activations