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

    Neuronpedia

    INDEX
    Explanations

    finding communities, lots, requests, hypotheses, blessings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boh
    0.51
    続
    0.46
     révol
    0.46
     بازی
    0.45
     Gottfried
    0.44
    㼛
    0.42
     rata
    0.42
     Ak
    0.42
     preferred
    0.41
     Soren
    0.41
    POSITIVE LOGITS
    核心
    0.47
    alth
    0.46
    真正
    0.46
    حن
    0.45
    체
    0.45
    在
    0.44
    解决
    0.43
     aérea
    0.43
    ayt
    0.43
    夏天
    0.42
    Act Density 0.001%

    No Known Activations