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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scolaire
    -0.54
     the
    -0.54
     Weller
    -0.53
     a
    -0.50
    iciens
    -0.48
     Justice
    -0.48
    Traducción
    -0.47
     scolaires
    -0.46
    cshtml
    -0.45
    +#+#
    -0.45
    POSITIVE LOGITS
     come
    0.63
    tvguidetime
    0.60
     المعيارى
    0.58
     Réponses
    0.57
     يتيمه
    0.57
     חיצוניים
    0.56
     Comes
    0.54
     ujednoznacz
    0.54
    اریخ
    0.53
     store
    0.52
    Act Density 0.003%

    No Known Activations