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

    Neuronpedia

    INDEX
    Explanations

    warrant

    np_max-act · gemini-2.0-flash

    This neuron never activates on any text—it doesn’t detect or respond to any token pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Info
    -0.07
    ZO
    -0.07
    či
    -0.07
     diets
    -0.06
    adio
    -0.06
    payments
    -0.06
    IO
    -0.06
     řekla
    -0.06
    Io
    -0.06
    누
    -0.06
    POSITIVE LOGITS
     warrant
    0.10
     warrants
    0.09
     warranted
    0.08
     Sent
    0.08
     WARRANT
    0.08
     Dexter
    0.07
     wre
    0.07
     UT
    0.07
     Worldwide
    0.07
     �
    0.07
    Act Density 0.002%

    No Known Activations