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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical values and formatting in data entries

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

    code and math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.49
    matchCondition
    -0.48
    новниш
    -0.46
     snippetHide
    -0.46
     resourceCulture
    -0.43
     '{@
    -0.43
    $}}
    -0.42
    })->
    -0.41
    InstrumentedTest
    -0.41
    OGND
    -0.40
    POSITIVE LOGITS
     Italijani
    0.44
    
    0.43
    :+:
    0.43
    тябрь
    0.37
    文
    0.36
    ThroughAttribute
    0.36
     neta
    0.36
    FunctionFlags
    0.36
     readline
    0.35
     considere
    0.34
    Act Density 0.000%

    No Known Activations