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

    Neuronpedia

    INDEX
    Explanations

    augment

    np_max-act · gemini-2.0-flash

    This neuron responds to words that mean “to add to” or “supplement,” such as augment, assist, or supplement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Τα
    -0.07
     ذ
    -0.07
     रहन
    -0.07
    変
    -0.07
    Ц
    -0.06
    edla
    -0.06
    Resp
    -0.06
    Backup
    -0.06
    рива
    -0.06
    _TRANS
    -0.06
    POSITIVE LOGITS
     Catholics
    0.07
    atal
    0.07
     ers
    0.06
    ив
    0.06
     Serge
    0.06
    complete
    0.06
    ;;;;;;
    0.06
    (propertyName
    0.06
     Mikhail
    0.06
     commerce
    0.06
    Act Density 0.021%

    No Known Activations