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

    Neuronpedia

    INDEX
    Explanations

    instances of namespaces or domain-like structures in code

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

    android library and package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.40
     remp
    -0.32
     Himo
    -0.32
     raised
    -0.31
    cuentes
    -0.30
     poils
    -0.30
     soigne
    -0.30
    }\}$
    -0.30
    )}-
    -0.29
    ]+$
    -0.29
    POSITIVE LOGITS
     AssemblyProduct
    0.60
     AssemblyCompany
    0.59
     للاسماء
    0.58
     otomatig
    0.56
     CanadaChoose
    0.48
    mergeFrom
    0.48
     հղումներ
    0.48
    enfone
    0.48
     <<<<<<<<<<<<<<
    0.48
    RTLR
    0.48
    Act Density 0.004%

    No Known Activations