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

    Neuronpedia

    INDEX
    Explanations

    /npm

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive and does not detect any pattern (it never fires).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .BorderFactory
    -0.07
    datetime
    -0.07
    _details
    -0.07
    arbeit
    -0.06
    _serializer
    -0.06
     credentials
    -0.06
    तर
    -0.06
    添
    -0.06
    Witness
    -0.06
     hopping
    -0.06
    POSITIVE LOGITS
    /npm
    0.07
    $insert
    0.06
    餐
    0.06
    ˆ
    0.06
     forb
    0.06
    436
    0.06
     unheard
    0.05
    Kenn
    0.05
     chết
    0.05
     forcibly
    0.05
    Act Density 0.001%

    No Known Activations