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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia articles

    np_max-act · gemini-2.0-flash

    This neuron does not activate for any tokens in the samples—it appears to be effectively inactive.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hlad
    -0.07
    .gsub
    -0.07
     кількості
    -0.07
     VOL
    -0.06
    (_)
    -0.06
    Par
    -0.06
    ุธ
    -0.06
    URES
    -0.06
    _subtitle
    -0.06
     interp
    -0.06
    POSITIVE LOGITS
    -book
    0.07
    irk
    0.06
     meantime
    0.06
    plants
    0.06
    eler
    0.06
    ,n
    0.06
     intuit
    0.06
    ункци
    0.06
     NTN
    0.06
     anne
    0.06
    Act Density 0.002%

    No Known Activations