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

    Neuronpedia

    INDEX
    Explanations

    attenuates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     will
    0.45
     enzim
    0.44
     my
    0.44
     decolor
    0.43
     ہوجائیں
    0.43
     Enzyme
    0.43
     Revisited
    0.42
     caspase
    0.42
     Ingredient
    0.41
     enzyme
    0.41
    POSITIVE LOGITS
    ロッパ
    0.51
    agedy
    0.48
    訾
    0.48
    パック
    0.47
    一座
    0.47
    WallArray
    0.46
    イビー
    0.46
    椑
    0.45
    iejęt
    0.45
    Perm
    0.45
    Act Density 0.001%

    No Known Activations