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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of matrix dimensions or indexing terms, especially “row” and “column.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prediction
    -0.07
    .x
    -0.07
    系统
    -0.07
    .button
    -0.06
    anan
    -0.06
    .trailing
    -0.06
    -man
    -0.06
    ()?>
    -0.06
    -ahead
    -0.06
    .nativeElement
    -0.06
    POSITIVE LOGITS
    Сам
    0.07
    .’”↵↵
    0.06
    )."
    0.06
    ]",
    0.06
     Supern
    0.06
    чів
    0.06
    !")↵↵
    0.06
    achinery
    0.06
    ")↵↵↵
    0.06
    qty
    0.06
    Act Density 0.010%

    No Known Activations