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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with performance metrics or settings

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

    line numbers @@

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.69
     Italijanski
    -0.69
    transQ
    -0.69
     laſſen
    -0.60
    LayoutStyle
    -0.58
    MethodManager
    -0.57
     Geſch
    -0.56
    ptonshire
    -0.55
    ArgumentParser
    -0.52
    OGND
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.44
     '\\;'
    0.38
    AndEndTag
    0.37
    Tē
    0.33
    期刊论文
    0.32
    ChildScrollView
    0.31
    StoreMessageInfo
    0.31
     समीक्षाओं
    0.31
     OMITBAD
    0.30
     indexes
    0.30
    Act Density 0.010%

    No Known Activations