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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash

    This neuron highlights numeric and statistical result tokens—especially numbers, percentages, and p-value notations in scientific findings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ीए
    -0.07
    _within
    -0.06
     Bac
    -0.06
    標準
    -0.06
     invading
    -0.06
    aciones
    -0.06
     Entwicklung
    -0.06
    :Set
    -0.06
     Vice
    -0.06
    POSITIVE LOGITS
     signin
    0.07
    =temp
    0.07
    -cols
    0.07
     toned
    0.07
    '}).
    0.06
    ()?;↵
    0.06
     ]];
    0.06
     {
↵
    0.06
    .firebase
    0.06
     Persona
    0.06
    Act Density 0.017%

    No Known Activations