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

    Neuronpedia

    INDEX
    Explanations

    roles and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onies
    0.39
    Dr
    0.38
    風味
    0.37
    出于
    0.36
    遊び
    0.36
    ご
    0.36
    悪
    0.35
    liches
    0.34
    UTHERN
    0.34
    (':
    0.34
    POSITIVE LOGITS
    ळ्यात
    0.48
    푚
    0.44
     президен
    0.43
     president
    0.40
     $\|\
    0.40
    घाटन
    0.40
     reforma
    0.40
    いろいろ
    0.39
     presidents
    0.38
     presiden
    0.37
    Act Density 0.000%

    No Known Activations