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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any tokens and thus does not detect any specific pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Chloe
    -0.07
    isma
    -0.07
    xyz
    -0.06
     assistant
    -0.06
     Presidential
    -0.06
    	op
    -0.06
    aç
    -0.06
    .key
    -0.06
    (col
    -0.06
    фек
    -0.06
    POSITIVE LOGITS
    (startDate
    0.08
     bestowed
    0.07
    ="-
    0.06
     tématu
    0.06
     برخ
    0.06
     =>$
    0.06
    Watcher
    0.06
    ebb
    0.06
    etailed
    0.06
    \F
    0.06
    Act Density 0.155%

    No Known Activations