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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron never fires (all activations are zero), so it appears to be effectively “dead” and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .streaming
    -0.07
    Archive
    -0.07
    -select
    -0.07
     totally
    -0.06
    yped
    -0.06
    etal
    -0.06
    &amp
    -0.06
    (Item
    -0.06
     псих
    -0.06
    _employee
    -0.06
    POSITIVE LOGITS
     buluş
    0.07
    .services
    0.06
    bron
    0.06
     albeit
    0.06
    .Assertions
    0.06
     Moran
    0.06
     Alvarez
    0.06
     नए
    0.06
     holy
    0.06
    ชาว
    0.06
    Act Density 0.176%

    No Known Activations