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

    Neuronpedia

    INDEX
    Explanations

    Code and pet descriptions

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive—it never responds (all activations remain zero), so it doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kennen
    -0.07
    weighted
    -0.07
     自动生成
    -0.07
     polít
    -0.06
     призна
    -0.06
    سوب
    -0.06
    不要
    -0.06
     wordt
    -0.06
     wissen
    -0.06
     tròn
    -0.06
    POSITIVE LOGITS
    uegos
    0.07
     Korean
    0.07
    _ne
    0.07
    iae
    0.06
     Miguel
    0.06
     lance
    0.06
     chia
    0.06
     apple
    0.06
     gerçek
    0.06
    eenth
    0.06
    Act Density 0.001%

    No Known Activations