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

    Neuronpedia

    INDEX
    Explanations

    future and possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।--
    0.45
    াহিদ
    0.43
    𝔂
    0.43
    TEGER
    0.42
    नावली
    0.41
     visibility
    0.38
     znacznie
    0.38
    湍
    0.38
     მაშინ
    0.38
     partir
    0.37
    POSITIVE LOGITS
     releasing
    0.39
     conserving
    0.39
     البل
    0.39
    லாத
    0.37
     ghép
    0.37
    thru
    0.36
    hop
    0.36
    twist
    0.35
    ベクトル
    0.34
    soph
    0.34
    Act Density 0.000%

    No Known Activations