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

    Neuronpedia

    INDEX
    Explanations

    HTML select elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పాత్ర
    0.46
    價值
    0.45
     قيمة
    0.41
     최
    0.40
    setValue
    0.40
     đẩy
    0.40
    役
    0.40
     ఆ
    0.39
     కని
    0.39
     Value
    0.39
    POSITIVE LOGITS
    createStatement
    0.39
     carbon
    0.39
    SIZ
    0.37
    צב
    0.37
     sediment
    0.36
    グリ
    0.36
    unc
    0.35
     fam
    0.35
    Carbon
    0.35
    胖
    0.35
    Act Density 0.000%

    No Known Activations