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

    Neuronpedia

    INDEX
    Explanations

    comp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kloped
    -0.48
    resar
    -0.47
    nasel
    -0.47
     fire
    -0.46
     ordinaire
    -0.44
    ziek
    -0.43
     past
    -0.43
    <bos>
    -0.43
     samh
    -0.42
     mothers
    -0.42
    POSITIVE LOGITS
    ScopeManager
    0.84
    AxisAlignment
    0.73
     MainAxisSize
    0.71
    InSection
    0.66
    NameInMap
    0.64
     للاسماء
    0.63
     CreateTagHelper
    0.63
     Himo
    0.60
     EconPapers
    0.60
    EndContext
    0.60
    Act Density 0.024%

    No Known Activations