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

    Neuronpedia

    INDEX
    Explanations

    Data analysis

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of data‐manipulation and modeling terms—e.g. “data,” “table,” “pandas,” “model,” “dataset,” “summary”—i.e. references to data‐frame libraries or pre-trained model code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Tok
    -0.07
    Warnings
    -0.06
    웠
    -0.06
     нес
    -0.06
    ublisher
    -0.06
     м
    -0.06
     slag
    -0.06
     denn
    -0.06
    _hor
    -0.06
    te
    -0.06
    POSITIVE LOGITS
    )는
    0.07
     honestly
    0.07
    .setStroke
    0.06
     Decompiled
    0.06
    是一个
    0.06
     rámci
    0.06
    _timezone
    0.06
     Transit
    0.06
    (Target
    0.06
     Aluminum
    0.06
    Act Density 0.042%

    No Known Activations