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

    Neuronpedia

    INDEX
    Explanations

    defined or of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     darte
    -0.56
    HtmlAttribute
    -0.55
     knowing
    -0.55
    Revenir
    -0.54
    :"-"`
    -0.49
     pasado
    -0.49
     المعيارى
    -0.48
     previous
    -0.46
    Demikian
    -0.46
     past
    -0.46
    POSITIVE LOGITS
     HasFactory
    0.68
    awtextra
    0.64
     Мексичка
    0.60
    complexContent
    0.60
    bootstrapcdn
    0.54
    LLocation
    0.53
    GroupLayout
    0.50
     honnête
    0.49
    GEBURTSDATUM
    0.49
    ########.
    0.49
    Act Density 0.005%

    No Known Activations