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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references

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

    bracketed identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umbersome
    -0.49
    uxxxx
    -0.48
    transQ
    -0.47
     betweenstory
    -0.46
    IVEREF
    -0.46
    RegressionTest
    -0.46
     useEffect
    -0.43
    uminescence
    -0.43
    ccione
    -0.42
    ADRID
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.53
    DockStyle
    0.52
    \"]
    0.43
    leyeb
    0.40
    })();
    0.39
    SizeF
    0.39
    ']))
    0.39
     rav
    0.38
     clearly
    0.38
     μπο
    0.37
    Act Density 0.142%

    No Known Activations