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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects taxonomic classification markers—tokens and phrases that denote ranks and placement (e.g. “family,” “genus,” “order,” “subfamily,” “tribe,” “placed in,” “belongs to,” “classified as,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cub
    -0.07
     SingleChildScrollView
    -0.07
    .Title
    -0.06
     lut
    -0.06
    рій
    -0.06
     Functor
    -0.06
    Encode
    -0.06
     SA
    -0.06
     nrows
    -0.06
     있었
    -0.06
    POSITIVE LOGITS
    ใ
    0.07
    Concrete
    0.06
     diğer
    0.06
    -special
    0.06
     Pu
    0.06
    ilen
    0.06
    �
    0.06
    imagen
    0.06
     Tet
    0.06
     erotische
    0.06
    Act Density 0.007%

    No Known Activations