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

    Neuronpedia

    INDEX
    Explanations

    malfunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collapsing
    -0.89
     falling
    -0.86
     leaking
    -0.79
    antaranya
    -0.77
     تضيفلها
    -0.76
    falling
    -0.75
    passing
    -0.69
     crumbling
    -0.68
    Життєпис
    -0.68
    pography
    -0.66
    POSITIVE LOGITS
    CopyWith
    0.60
    GraphicsUnit
    0.59
    memoized
    0.54
     rés
    0.51
    XmlEnum
    0.50
    Джерела
    0.49
    gwt
    0.49
     незавершена
    0.48
    WriteAttribute
    0.48
     prepar
    0.46
    Act Density 0.049%

    No Known Activations