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

    Neuronpedia

    INDEX
    Explanations

    lib

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the H.264 video codec (the “libx264” setting) in ffmpeg command arguments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Crane
    -0.08
     deix
    -0.06
    шев
    -0.06
    errat
    -0.06
     서비스
    -0.06
    ại
    -0.06
    _pan
    -0.06
    domains
    -0.06
    >Select
    -0.06
     Flem
    -0.06
    POSITIVE LOGITS
     investment
    0.07
    Much
    0.07
    ++){↵↵
    0.07
     back
    0.07
    -made
    0.06
    aired
    0.06
     ],↵
    0.06
    -haired
    0.06
    .intersection
    0.06
    ा↵↵
    0.06
    Act Density 0.001%

    No Known Activations