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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit or violent content requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grant
    0.35
     Mim
    0.33
    不成
    0.32
     Carnival
    0.32
     Marina
    0.32
     Deck
    0.32
    —
    0.32
     Commission
    0.31
     Eng
    0.31
     Warner
    0.31
    POSITIVE LOGITS
     polypeptides
    0.39
     conformations
    0.37
     antisymmetric
    0.37
     petrochemical
    0.36
    acch
    0.34
    ギー
    0.34
     systematics
    0.34
     appreciably
    0.33
     alken
    0.33
    commutative
    0.33
    Act Density 0.001%

    No Known Activations