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

    Neuronpedia

    INDEX
    Explanations

    inherently dangerous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    မယ်
    0.44
    lim
    0.43
     emotional
    0.42
    Unsupported
    0.42
    aredo
    0.42
    ਲਾਂ
    0.42
     ビジネス
    0.42
    🥢
    0.41
    timelist
    0.40
    emotional
    0.40
    POSITIVE LOGITS
    不变
    0.52
     فرق
    0.48
     revise
    0.48
    变化
    0.46
    连
    0.46
    蚀
    0.44
    更改
    0.44
    边
    0.44
    简单
    0.43
     revised
    0.43
    Act Density 0.000%

    No Known Activations