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

    Neuronpedia

    INDEX
    Explanations

    wtf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.86
     للمعارف
    -0.71
     CreateTagHelper
    -0.69
    omeness
    -0.69
    DoubleQuotes
    -0.68
    RTEX
    -0.62
     Hermitage
    -0.59
    Démographie
    -0.57
     Ambiental
    -0.57
     Magdalen
    -0.57
    POSITIVE LOGITS
     him
    0.54
    AutoScaleMode
    0.52
    JoinTable
    0.48
     ExecuteAsync
    0.45
    TargetApi
    0.44
    ManyToMany
    0.44
    LinkId
    0.43
    actin
    0.43
    DispatchQueue
    0.42
    qrst
    0.41
    Act Density 0.003%

    No Known Activations