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

    Neuronpedia

    INDEX
    Explanations

    Finding something

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens, so it isn’t detecting any pattern—it’s essentially inactive.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    浴
    -0.06
    _Att
    -0.06
     spokeswoman
    -0.06
    ancestor
    -0.06
    410
    -0.06
    ้อม
    -0.06
     spokesman
    -0.06
     Odd
    -0.06
     respected
    -0.06
     resourceId
    -0.06
    POSITIVE LOGITS
     euth
    0.07
     NASA
    0.06
    ρκ
    0.06
     vacc
    0.06
     remains
    0.06
     Caf
    0.06
     nombre
    0.06
    [array
    0.06
    pixel
    0.06
    -redux
    0.06
    Act Density 0.008%

    No Known Activations