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

    Neuronpedia

    INDEX
    Explanations

    units of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     واکنش
    0.49
    quando
    0.47
     уров
    0.45
     반응
    0.45
     পাঠানো
    0.45
     étro
    0.44
     امکان
    0.43
     Луч
    0.43
     úrov
    0.43
     quand
    0.43
    POSITIVE LOGITS
    坦
    0.42
     Herc
    0.41
    籍
    0.41
    ravel
    0.40
     exercising
    0.38
     ambiental
    0.38
    ล้ว
    0.37
    transferase
    0.37
    اتج
    0.36
    撸
    0.36
    Act Density 0.010%

    No Known Activations