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

    Neuronpedia

    INDEX
    Explanations

    high measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     گیر
    0.36
    Фе
    0.35
    ⵄ
    0.35
    *>(
    0.35
    endom
    0.35
     atha
    0.35
    >**
    0.35
     Backward
    0.34
    obe
    0.34
     اٹ
    0.34
    POSITIVE LOGITS
    High
    1.68
     High
    1.66
     highs
    1.58
     high
    1.53
    high
    1.43
     हाई
    1.33
    高
    1.32
    HIGH
    1.25
    最高
    1.23
     HIGH
    1.16
    Act Density 0.019%

    No Known Activations