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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical publications

    np_max-act · gemini-2.0-flash

    The neuron activates on fragments of systematic chemical compound names—especially IUPAC‐style tokens (numbers, hyphens, and substituent prefixes) that form part of a full chemical name.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thử
    -0.06
     immunity
    -0.06
     veh
    -0.06
     Tài
    -0.06
     sexist
    -0.06
    _abs
    -0.06
     viewing
    -0.06
     terse
    -0.06
     tape
    -0.06
    олее
    -0.06
    POSITIVE LOGITS
     listOf
    0.06
    [M
    0.06
     Place
    0.06
     کری
    0.06
     PLACE
    0.06
    VERS
    0.06
     statues
    0.06
    ellij
    0.06
     ситуации
    0.06
     Cum
    0.06
    Act Density 0.010%

    No Known Activations