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

    Neuronpedia

    INDEX
    Explanations

    families

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uttered
    0.38
    standard
    0.37
    ScheduledAction
    0.36
    ava
    0.36
    aboration
    0.35
    Object
    0.35
    Time
    0.35
     Сам
    0.35
     entschieden
    0.35
    远
    0.34
    POSITIVE LOGITS
    族的
    0.44
    妠
    0.38
    ribut
    0.36
    vodu
    0.35
    ങ്ങനെ
    0.35
    wiata
    0.35
    jell
    0.35
     الوضع
    0.35
     맞
    0.34
     Datos
    0.34
    Act Density 0.000%

    No Known Activations