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

    Neuronpedia

    INDEX
    Explanations

    single-digit numbers

    np_max-act · gemini-2.0-flash

    This neuron specifically detects numeric locant tokens (digits like “8” and “5”) in chemical compound names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms related to chemical compound production processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uminium
    -0.07
    rels
    -0.07
     �
    -0.06
    /network
    -0.06
    Navigator
    -0.06
    .Table
    -0.06
    ?>
    -0.06
    (kernel
    -0.06
    gae
    -0.06
    Knife
    -0.06
    POSITIVE LOGITS
    ετ
    0.07
     dur
    0.07
    	tab
    0.06
    .Tab
    0.06
     Mey
    0.06
    gb
    0.06
     pediatric
    0.06
     tot
    0.06
     ар
    0.06
    _Cl
    0.06
    Act Density 0.033%

    No Known Activations