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

    Neuronpedia

    INDEX
    Explanations

    scientific names

    np_max-act · gemini-2.0-flash

    This neuron activates on capitalized Latin genus names (scientific taxonomic names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    =z
    -0.07
    -0.07
     eyel
    -0.06
     Hep
    -0.06
    (headers
    -0.06
    rimp
    -0.06
     انج
    -0.06
    _cpus
    -0.06
    Ai
    -0.06
    _B
    -0.06
    POSITIVE LOGITS
    ักษณ
    0.07
     compromises
    0.07
     transitional
    0.06
     twists
    0.06
    assuming
    0.06
    459
    0.06
     bian
    0.06
     highway
    0.06
     Blanch
    0.06
    UME
    0.06
    Act Density 0.008%

    No Known Activations