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
     Specifically
    -0.45
     scatola
    -0.45
     Reliance
    -0.45
     fermés
    -0.45
    évaluateur
    -0.44
     Unknown
    -0.44
     précédentes
    -0.44
     tué
    -0.43
     décé
    -0.43
     Them
    -0.41
    POSITIVE LOGITS
     kaynağından
    0.65
     ExecuteAsync
    0.58
    itinéraire
    0.57
    bootstrapcdn
    0.57
    PyExc
    0.55
    WireFormatLite
    0.55
     selection
    0.54
    FileList
    0.54
     cref
    0.53
    참고
    0.53
    Act Density 0.006%

    No Known Activations