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

    Neuronpedia

    INDEX
    Explanations

    programming/technical text

    np_max-act · gemini-2.0-flash

    The neuron fires on technical programming‐documentation terms—especially file and library names (e.g. “file,” “liblzma,” “library”) in code comments or API headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tiğini
    -0.07
     Pee
    -0.07
     chew
    -0.07
    риф
    -0.07
    mav
    -0.06
    uality
    -0.06
    quarters
    -0.06
    obao
    -0.06
    crawler
    -0.06
     Kaf
    -0.06
    POSITIVE LOGITS
     Presented
    0.06
    UU
    0.06
    useppe
    0.06
     Amber
    0.06
     CPA
    0.06
     Jugend
    0.06
    elsinki
    0.06
    pedo
    0.06
    .ogg
    0.06
    >/<
    0.06
    Act Density 0.081%

    No Known Activations