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

    Neuronpedia

    INDEX
    Explanations

    Chemical formulas

    np_max-act · gemini-2.0-flash

    The neuron detects coordination‐mode annotations (e.g. “κO2,” “κS1”) in inorganic complex names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -makers
    -0.07
    (debug
    -0.07
    опис
    -0.06
     EPA
    -0.06
    庫
    -0.06
    -definition
    -0.06
    ravel
    -0.06
    zero
    -0.06
    adamente
    -0.06
    istributions
    -0.06
    POSITIVE LOGITS
     kick
    0.07
    	opts
    0.06
    utut
    0.06
     entertaining
    0.06
    .getItemId
    0.06
     порядку
    0.06
    _encoded
    0.06
     kill
    0.06
    ään
    0.06
    bsub
    0.06
    Act Density 0.004%

    No Known Activations