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

    Neuronpedia

    INDEX
    Explanations

    Avoid clichés

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.58
     anderer
    0.56
     Batterie
    0.48
    Become
    0.46
    衮
    0.45
    Project
    0.44
    Battery
    0.44
    Batter
    0.44
    Nuevo
    0.43
     gleiche
    0.42
    POSITIVE LOGITS
    нків
    0.49
     Forming
    0.47
     forming
    0.44
    куп
    0.44
    으로는
    0.43
     앞
    0.42
     Οι
    0.42
    떤
    0.42
     называ
    0.41
     합성
    0.41
    Act Density 0.000%

    No Known Activations