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

    Neuronpedia

    INDEX
    Explanations

    privacy and technical reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pazienti
    0.50
     adulti
    0.49
    луйста
    0.47
    িনবার্গ
    0.46
     occhi
    0.46
     hombres
    0.45
     tights
    0.45
    CORDS
    0.45
     jóvenes
    0.45
     représentent
    0.45
    POSITIVE LOGITS
    ó
    0.48
    ै
    0.46
     JA
    0.44
     SQLException
    0.41
     सूख
    0.40
    ম্মদ
    0.40
    ää
    0.39
    TrackAngle
    0.39
    ς
    0.39
    勢
    0.39
    Act Density 0.001%

    No Known Activations