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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash

    This neuron never activates on any of the tokens—it’s essentially a “dead” neuron that doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ráp
    -0.08
    уки
    -0.07
     misinformation
    -0.07
    [of
    -0.06
    AMP
    -0.06
    كار
    -0.06
    _Con
    -0.06
    inox
    -0.06
    chains
    -0.06
    №№
    -0.06
    POSITIVE LOGITS
     Laud
    0.07
     مواط
    0.06
     modele
    0.06
     برگزار
    0.06
    .Deserialize
    0.06
     første
    0.06
    (eventName
    0.06
    /{
    0.06
    車
    0.06
    orrar
    0.06
    Act Density 0.005%

    No Known Activations