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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    This neuron never fires—it does not activate on any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cps
    -0.07
    ателей
    -0.06
     bou
    -0.06
    (insert
    -0.06
    也是
    -0.06
     instanceof
    -0.06
    粗
    -0.06
     همراه
    -0.06
    totals
    -0.06
    Thanks
    -0.06
    POSITIVE LOGITS
    zza
    0.07
     карт
    0.07
     Tropical
    0.06
     Always
    0.06
    &
    0.06
    "."
    0.06
    izza
    0.06
     kuv
    0.06
    ainen
    0.06
    .Results
    0.06
    Act Density 0.040%

    No Known Activations