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

    Neuronpedia

    INDEX
    Explanations

    progression with each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Replacement
    0.43
    变成
    0.42
    원
    0.40
     Replacement
    0.39
    纸
    0.39
    first
    0.39
    replacement
    0.38
    變成
    0.38
     seater
    0.38
    defining
    0.38
    POSITIVE LOGITS
    かもしれません
    0.42
     zároveň
    0.39
     Besuch
    0.38
    गर्भ
    0.38
    ższ
    0.38
    🥃
    0.37
    戮
    0.36
    ")}}'
    0.36
    cura
    0.35
    ש
    0.35
    Act Density 0.000%

    No Known Activations