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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mark
    -0.08
    Tek
    -0.07
    ụp
    -0.07
     mashed
    -0.07
    .Simple
    -0.07
     Heating
    -0.07
     ruined
    -0.07
     nicknamed
    -0.06
    Jud
    -0.06
     dziew
    -0.06
    POSITIVE LOGITS
     náv
    0.06
    imální
    0.06
     rozhodnutí
    0.06
     unic
    0.06
    .Merge
    0.06
     ostatní
    0.06
    大學
    0.06
    .GetById
    0.06
    Files
    0.06
    _BAL
    0.06
    Act Density 0.152%

    No Known Activations