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

    Neuronpedia

    INDEX
    Explanations

    planning and considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuanced
    0.47
     Kesehatan
    0.46
    tolerance
    0.46
     добро
    0.45
     Frieden
    0.44
    ⇵
    0.44
     humanidad
    0.43
     философ
    0.42
    ယ့်
    0.42
     activism
    0.41
    POSITIVE LOGITS
     powy
    0.39
    幸
    0.39
    4
    0.39
    8
    0.39
    瞄
    0.38
    ilikom
    0.38
     ταιν
    0.38
    ここ
    0.37
    ഷ
    0.37
    0.37
    Act Density 0.001%

    No Known Activations