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

    Neuronpedia

    INDEX
    Explanations

    ethyl

    np_max-act · gemini-2.0-flash

    The neuron activates on chemical substituent fragments, especially alkyl group names like “ethyl” (e.g. in “bromo­methyl,” “ethyl”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     infant
    -0.07
     hijos
    -0.06
     holland
    -0.06
    _override
    -0.06
     disponible
    -0.06
     Zoom
    -0.06
     Lia
    -0.06
     contrace
    -0.06
    δες
    -0.06
     dest
    -0.06
    POSITIVE LOGITS
    Secret
    0.07
    ustain
    0.07
     Між
    0.07
    Gün
    0.07
    OPT
    0.07
     methyl
    0.07
     <",
    0.07
    _TXT
    0.07
    TextInput
    0.07
    .separator
    0.06
    Act Density 0.007%

    No Known Activations