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

    Neuronpedia

    INDEX
    Explanations

    towels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.59
    ViewFeatures
    -0.52
    quelize
    -0.49
     conversion
    -0.47
     muscles
    -0.47
    IsContent
    -0.46
    SizeF
    -0.45
    Хро
    -0.45
     slave
    -0.45
    ometric
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.73
     reservados
    0.52
    nal
    0.50
     morire
    0.50
     للمعارف
    0.50
     tombé
    0.49
    DockStyle
    0.48
     comporte
    0.47
    MethodManager
    0.47
    ɵɵ
    0.47
    Act Density 0.965%

    No Known Activations