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

    Neuronpedia

    INDEX
    Explanations

    employees acting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ფუნქ
    0.46
     Berechnung
    0.46
     Descripción
    0.44
     amplitud
    0.43
     ..$
    0.43
     calculateur
    0.42
    функциона
    0.41
    絠
    0.41
    descripcion
    0.41
     funcionalidad
    0.40
    POSITIVE LOGITS
     Lev
    0.47
     American
    0.42
    Click
    0.41
    BibitemShut
    0.41
     widely
    0.40
     despite
    0.40
     Ch
    0.39
    Lev
    0.39
     human
    0.39
     Penn
    0.39
    Act Density 0.000%

    No Known Activations