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

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.69
     MenuView
    -0.68
    colgroup
    -0.59
     carats
    -0.59
     MonoBehaviour
    -0.59
    FormTagHelper
    -0.59
    visiae
    -0.57
    enegro
    -0.57
     betweenstory
    -0.57
    <bos>
    -0.56
    POSITIVE LOGITS
     Roskov
    0.59
    Rüyada
    0.55
     cérami
    0.46
     traités
    0.40
    MENAFN
    0.39
     gång
    0.38
     ErrIntOverflow
    0.38
     Eing
    0.38
     förs
    0.38
    سي
    0.38
    Act Density 0.006%

    No Known Activations