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

    Neuronpedia

    INDEX
    Explanations

    success or failure outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     timet
    0.48
     outliers
    0.45
    hatti
    0.44
     kilow
    0.43
     collectibles
    0.43
    itri
    0.42
     tributes
    0.41
    蓯
    0.41
     cheating
    0.41
    苕
    0.41
    POSITIVE LOGITS
    Failure
    0.50
    失败
    0.50
    Success
    0.47
     errno
    0.46
     실패
    0.45
    Status
    0.43
    成功
    0.43
    FAILED
    0.42
    Fail
    0.41
    Failed
    0.41
    Act Density 0.224%

    No Known Activations