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

    Neuronpedia

    INDEX
    Explanations

    Math/code equations

    np_max-act · gemini-2.0-flash

    The neuron is essentially inactive—it does not reliably respond to any particular token or pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hottest
    -0.07
    iteit
    -0.06
    ριστ
    -0.06
    inci
    -0.06
     Erectile
    -0.06
    ､↵
    -0.06
     cruiser
    -0.06
    nické
    -0.06
    .vehicle
    -0.06
    oog
    -0.06
    POSITIVE LOGITS
     Ha
    0.07
    .LEADING
    0.06
     ieee
    0.06
    .nombre
    0.06
     DIRECT
    0.06
    hopefully
    0.06
     замен
    0.06
     жов
    0.06
     nodeId
    0.06
    .jasper
    0.06
    Act Density 0.016%

    No Known Activations