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

    Neuronpedia

    INDEX
    Explanations

    questions based

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሳሪያ
    0.56
     useAppContext
    0.50
    .??.??"]
    0.49
    は
    0.48
    鉾
    0.48
     กล่าว
    0.48
     Asalamualaikum
    0.47
     WindowStateType
    0.47
    波動方程式
    0.47
    은
    0.46
    POSITIVE LOGITS
    Percentage
    0.49
    Options
    0.49
    Other
    0.47
    Code
    0.47
    Score
    0.46
    zzles
    0.46
    samples
    0.46
    Some
    0.46
    Level
    0.46
    package
    0.46
    Act Density 0.000%

    No Known Activations