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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving powers and fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions with 2 and powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.71
     AssemblyCompany
    -0.69
    ThroughAttribute
    -0.67
    tagHelperRunner
    -0.63
     InputDecoration
    -0.60
    BeginContext
    -0.55
    OCCURRED
    -0.54
    出版年
    -0.52
    tagPool
    -0.52
     BorderRadius
    -0.51
    POSITIVE LOGITS
    )²
    0.54
    )^
    0.50
    })^{
    0.47
    )++;
    0.47
    )^{
    0.47
    })_{
    0.47
    })()
    0.46
    OGND
    0.46
    )[
    0.44
    )()
    0.41
    Act Density 0.365%

    No Known Activations