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

    Neuronpedia

    INDEX
    Explanations

    numerals

    np_max-act · gemini-2.0-flash

    The neuron activates on standalone numeric labels or section numbers marking the beginnings of numbered paragraphs or list items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    розум
    -0.07
    keydown
    -0.07
     الام
    -0.07
    iot
    -0.07
    _sur
    -0.07
    ichtet
    -0.06
     přibliž
    -0.06
    managedType
    -0.06
    ypo
    -0.06
     नक
    -0.06
    POSITIVE LOGITS
    ۲۰۱
    0.07
     Ala
    0.07
    oidal
    0.07
     Telecom
    0.07
    ived
    0.06
    dispose
    0.06
     trai
    0.06
    160
    0.06
     Georgia
    0.06
     fail
    0.06
    Act Density 0.003%

    No Known Activations