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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash

    This neuron is essentially “dead”—it never activates and doesn’t detect any patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     intellectual
    -0.06
    players
    -0.06
     egregious
    -0.06
     ذات
    -0.06
     Plzeň
    -0.06
     marketer
    -0.06
    진
    -0.06
    WT
    -0.06
    -commerce
    -0.06
    +i
    -0.06
    POSITIVE LOGITS
    .Networking
    0.08
    ange
    0.08
     없
    0.07
     Switch
    0.07
    (range
    0.07
     Courage
    0.07
    ANGE
    0.07
    maker
    0.07
     quant
    0.06
    Range
    0.06
    Act Density 0.003%

    No Known Activations