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

    Neuronpedia

    INDEX
    Explanations

    code structure elements such as function definitions and return statements

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

    determination of control value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.52
     }{@
    -0.41
     endforeach
    -0.41
    vfill
    -0.40
    MLLoader
    -0.40
     hefyd
    -0.39
    RMSE
    -0.38
    bibfield
    -0.38
    orki
    -0.37
    fjspx
    -0.37
    POSITIVE LOGITS
     CURIAM
    0.59
    enterOuterAlt
    0.56
    Personendaten
    0.54
    verifyException
    0.48
    RTSC
    0.47
    EDEFAULT
    0.46
     Paglinawan
    0.45
    PositiveButton
    0.45
    RegressionTest
    0.45
     ExecuteAsync
    0.44
    Act Density 0.043%

    No Known Activations