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

    Neuronpedia

    INDEX
    Explanations

    explains or describes situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     producteurs
    0.41
     sesize
    0.41
     galt
    0.40
     mari
    0.40
    luoromethyl
    0.40
     plastik
    0.40
    絃
    0.39
    휀
    0.39
    رياض
    0.39
     tissu
    0.38
    POSITIVE LOGITS
     Disp
    0.41
    Tart
    0.41
    disp
    0.40
    Disp
    0.39
    Years
    0.38
     засе
    0.38
    ulation
    0.37
    Annotation
    0.37
     sacred
    0.37
    Boxes
    0.37
    Act Density 0.001%

    No Known Activations