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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron detects technical terms—especially scientific species names, chemical substances, or acronyms—that appear immediately before or inside parentheses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Lock
    -0.07
    _armor
    -0.07
    )&&(
    -0.07
    Stmt
    -0.07
     imshow
    -0.06
    _suspend
    -0.06
    纯
    -0.06
    orado
    -0.06
    -list
    -0.06
    mast
    -0.06
    POSITIVE LOGITS
     femin
    0.07
    오
    0.07
     放
    0.06
    �
    0.06
    ?f
    0.06
     earthly
    0.06
    imiters
    0.06
    edení
    0.06
     раньше
    0.06
    كة
    0.06
    Act Density 0.041%

    No Known Activations