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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron specifically detects mentions of Type Ia supernovae (words like “Type I,” “supernova,” “Ia”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ocak
    -0.06
     TORT
    -0.06
    ização
    -0.06
    .MM
    -0.06
     başlay
    -0.06
    .lucene
    -0.06
     ark
    -0.06
    arton
    -0.06
     dann
    -0.06
     copied
    -0.06
    POSITIVE LOGITS
    ait
    0.07
    (EIF
    0.07
    ]++;↵
    0.07
    ,/
    0.07
     sizing
    0.06
    esehen
    0.06
     específ
    0.06
    意
    0.06
    elopment
    0.06
     beck
    0.06
    Act Density 0.002%

    No Known Activations