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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive—it does not respond to any tokens and never fires.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CI
    -0.06
    unicode
    -0.06
     Flores
    -0.06
     babys
    -0.06
    ํ
    -0.05
     mij
    -0.05
    -analytics
    -0.05
     pand
    -0.05
    ////////////////////////////////////////////////////////////////
    -0.05
     fis
    -0.05
    POSITIVE LOGITS
     luego
    0.07
     Maint
    0.07
     eigentlich
    0.06
    _created
    0.06
     étaient
    0.06
    arth
    0.06
    .Il
    0.06
    apgolly
    0.06
    fois
    0.06
     лицо
    0.06
    Act Density 0.044%

    No Known Activations