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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the intricacies of technical explanations and their implications

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

    Explaining reasons and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.45
     Allociné
    -0.39
    tagHelperRunner
    -0.38
    UrlResolution
    -0.37
    tahui
    -0.36
    ství
    -0.34
    InstrumentedTest
    -0.33
    CommandText
    -0.33
    épendance
    -0.33
    setAlignment
    -0.33
    POSITIVE LOGITS
    oredCriteria
    0.45
    astéroïdes
    0.43
     ivelany
    0.43
    IndentedString
    0.43
     CWE
    0.42
     bParam
    0.42
    rinth
    0.41
     HFILL
    0.40
    djangoproject
    0.40
    /**
    0.40
    Act Density 0.250%

    No Known Activations