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

    Neuronpedia

    INDEX
    Explanations

    rates of change or potential growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]:
    0.45
    nity
    0.45
     Fears
    0.45
    ſh
    0.44
    ওয়্যার
    0.44
     หา
    0.43
     букмекерлик
    0.43
     May
    0.43
     Dec
    0.42
     นิ
    0.42
    POSITIVE LOGITS
     masts
    0.48
    ي
    0.47
     indigenous
    0.47
    ıldı
    0.45
     altri
    0.44
     palettes
    0.43
    elter
    0.41
    蘚
    0.41
    血管
    0.41
     strawberry
    0.41
    Act Density 0.000%

    No Known Activations