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

    Neuronpedia

    INDEX
    Explanations

    electronic harassment and autoimmune diseases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kertas
    0.62
    ଵ
    0.53
     siis
    0.50
    🗼
    0.48
     Artikel
    0.48
     giày
    0.47
     braucht
    0.47
     könnt
    0.47
     átomos
    0.46
     kellett
    0.46
    POSITIVE LOGITS
    En
    0.52
    DC
    0.51
    It
    0.50
    System
    0.50
    Modifier
    0.49
     Vance
    0.48
    International
    0.46
    7
    0.46
    Op
    0.46
    An
    0.46
    Act Density 0.000%

    No Known Activations