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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of file‐ or data‐size information (e.g. “size,” “sized,” “MB,” numeric size values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mingle
    -0.07
    히
    -0.06
     Scanner
    -0.06
    력
    -0.06
    ز
    -0.06
    (display
    -0.06
     Phones
    -0.06
    _console
    -0.06
     categorical
    -0.06
    	ERROR
    -0.06
    POSITIVE LOGITS
    装置
    0.07
     interoper
    0.06
    ');↵↵↵↵
    0.06
    _rem
    0.06
     arrive
    0.06
    (simp
    0.06
     alan
    0.06
    234
    0.06
     onSuccess
    0.06
     trilogy
    0.06
    Act Density 0.020%

    No Known Activations