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

    Neuronpedia

    INDEX
    Explanations

    Equations

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not respond to any token (it’s essentially “dead”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ايران
    -0.07
    组织
    -0.06
     newbie
    -0.06
    _extend
    -0.06
    itbart
    -0.06
    міну
    -0.06
     believed
    -0.06
     smugg
    -0.06
    jím
    -0.06
    converted
    -0.06
    POSITIVE LOGITS
     controle
    0.07
     možnost
    0.06
    (priority
    0.06
     numeral
    0.06
     mimetype
    0.06
     Manning
    0.06
     Senators
    0.06
    itt
    0.06
     JL
    0.06
    Đối
    0.06
    Act Density 0.058%

    No Known Activations