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

    Neuronpedia

    INDEX
    Explanations

    scoring/time

    np_max-act · gemini-2.0-flash

    This neuron responds to ordinal indicators (e.g. “first,” “second,” “third”) marking positions or phases, especially in sports contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    say
    -0.07
    .Pattern
    -0.07
     affair
    -0.07
     bull
    -0.07
    "This
    -0.06
     Midwest
    -0.06
     言
    -0.06
    数字
    -0.06
    ScreenWidth
    -0.06
     significance
    -0.06
    POSITIVE LOGITS
    conds
    0.07
    voor
    0.07
    \r
    0.06
    """↵↵↵
    0.06
     nghiên
    0.06
    _TXT
    0.06
    )";
↵
    0.06
    Newton
    0.06
     Heller
    0.06
     pocit
    0.06
    Act Density 0.003%

    No Known Activations