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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pitchers
    -0.07
     Vincent
    -0.07
     Form
    -0.07
     nests
    -0.06
     лечения
    -0.06
    Booking
    -0.06
     onSave
    -0.06
    Representation
    -0.06
    hoc
    -0.06
     تنظیم
    -0.06
    POSITIVE LOGITS
     labeled
    0.07
    errupt
    0.06
     Trainer
    0.06
    /stretch
    0.06
     HK
    0.06
    مانی
    0.06
    立て
    0.06
     επίσης
    0.06
    _PAGE
    0.06
    actually
    0.05
    Act Density 0.100%

    No Known Activations