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

    Neuronpedia

    INDEX
    Explanations

    defining or listing elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    compassing
    0.38
    pecies
    0.37
     lineColorSpace
    0.35
     पूछता
    0.35
     also
    0.35
    तों
    0.35
     वर्च
    0.34
    त
    0.34
    лим
    0.34
    諜
    0.33
    POSITIVE LOGITS
    该
    0.50
    勖
    0.41
    这
    0.41
    技术
    0.39
    这种
    0.38
     অব
    0.38
    ωση
    0.38
     Teknik
    0.38
    resourceUrl
    0.37
    返回值
    0.37
    Act Density 0.003%

    No Known Activations