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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash

    This neuron detects Makefile compile‐recipe lines invoking the compiler with the “-c” flag.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     jedno
    -0.07
     mannen
    -0.07
    otr
    -0.07
    ków
    -0.06
    альное
    -0.06
     انگ
    -0.06
     hlavní
    -0.06
     RequestOptions
    -0.06
    ledi
    -0.06
     Mey
    -0.06
    POSITIVE LOGITS
    (board
    0.06
    .ret
    0.06
     explains
    0.06
    负
    0.06
     cx
    0.06
     commem
    0.06
     Recipes
    0.06
     βο
    0.06
    Patterns
    0.06
    戒
    0.06
    Act Density 0.001%

    No Known Activations