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

    Neuronpedia

    INDEX
    Explanations

    code examples and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最初に
    0.44
    िको
    0.42
     мин
    0.42
    arl
    0.41
    นิด
    0.41
    飽
    0.41
    alsa
    0.41
    OR
    0.40
    FC
    0.40
    FP
    0.39
    POSITIVE LOGITS
     poche
    0.46
     tiktok
    0.46
     poin
    0.45
     方法
    0.44
     themed
    0.43
     street
    0.43
     point
    0.42
     linings
    0.42
     skateboarding
    0.42
     Analysts
    0.41
    Act Density 0.004%

    No Known Activations