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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.67
    eleri
    -0.58
    Visits
    -0.56
    Observers
    -0.55
     Rech
    -0.53
     opérateur
    -0.53
    TouchEvent
    -0.52
     Drawable
    -0.51
    interpreter
    -0.51
     négy
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.55
     surla
    0.54
     ddelweddau
    0.54
     समीक्षाओं
    0.54
    DoubleQuotes
    0.53
     success
    0.50
    ništ
    0.49
     informée
    0.49
     progress
    0.48
    XmlAccessType
    0.48
    Act Density 0.003%

    No Known Activations