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

    Neuronpedia

    INDEX
    Explanations

    correct

    np_max-act · gemini-2.0-flash

    The neuron activates on programming‐language import/include directives (e.g. “#include”, “import …;”) and code file headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ubergraph
    -0.07
     सक
    -0.06
    .commands
    -0.06
     UICollectionView
    -0.06
     رو
    -0.06
    思い
    -0.06
    Token
    -0.06
     편
    -0.06
     Vale
    -0.06
    字
    -0.06
    POSITIVE LOGITS
    tz
    0.07
    екс
    0.07
    етель
    0.07
     correctly
    0.07
     ali
    0.07
    (self
    0.07
     poster
    0.06
     Setting
    0.06
     توم
    0.06
    (Address
    0.06
    Act Density 0.027%

    No Known Activations