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

    Neuronpedia

    INDEX
    Explanations

    scientific, technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are parts of chemical compound names (IUPAC-style nomenclature).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     owl
    -0.07
     Jenny
    -0.06
    .likes
    -0.06
     drowned
    -0.06
     Dead
    -0.06
     Glenn
    -0.06
     غير
    -0.06
    infeld
    -0.06
    _bonus
    -0.06
    -cl
    -0.06
    POSITIVE LOGITS
     аль
    0.06
    [token
    0.06
     estimating
    0.06
     سریع
    0.06
    Dataset
    0.06
     Вік
    0.06
    .getExternal
    0.06
    !/
    0.06
     pollutants
    0.06
    enzyme
    0.06
    Act Density 0.029%

    No Known Activations