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

    Neuronpedia

    INDEX
    Explanations

    partner in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulators
    0.84
     bunk
    0.83
     enemies
    0.82
     dozens
    0.82
     products
    0.79
     neighbors
    0.78
     apa
    0.76
     해당
    0.75
     racking
    0.74
     ねえ
    0.74
    POSITIVE LOGITS
     Все
    0.80
     All
    0.77
    All
    0.76
    compact
    0.74
    Alles
    0.72
    Все
    0.72
    èce
    0.71
     Держа
    0.71
     Roll
    0.71
    Standing
    0.70
    Act Density 0.002%

    No Known Activations