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

    Neuronpedia

    INDEX
    Explanations

    custom sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compres
    0.41
     renovación
    0.40
     ایپل
    0.39
     investasi
    0.38
     bisnis
    0.36
     изображение
    0.36
     Them
    0.36
     सफेद
    0.36
    ハード
    0.36
     handels
    0.36
    POSITIVE LOGITS
     spanned
    0.40
    int
    0.39
    ara
    0.38
    IntVar
    0.38
    left
    0.38
    anything
    0.37
    ab
    0.36
    item
    0.36
    agam
    0.36
    akes
    0.35
    Act Density 0.000%

    No Known Activations