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

    Neuronpedia

    INDEX
    Explanations

    Taxonomy

    np_max-act · gemini-2.0-flash

    The neuron fires on Latin taxonomic names, especially scientific family- and higher-level classification terms (e.g. names ending in –aceae, –idae, –ales, –idea).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PCODE
    -0.07
     acuerdo
    -0.07
     µ
    -0.07
    _correct
    -0.07
     Photos
    -0.06
     gradient
    -0.06
    �
    -0.06
     pendant
    -0.06
    _POINTER
    -0.06
    ět
    -0.06
    POSITIVE LOGITS
     Stra
    0.07
    -binding
    0.06
     dying
    0.06
     Houses
    0.06
     Foster
    0.06
     Bair
    0.06
     sticking
    0.06
    trying
    0.06
    �始化
    0.06
    團
    0.06
    Act Density 0.013%

    No Known Activations