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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive—it does not reliably detect any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     materiál
    -0.07
     конкур
    -0.07
    JOR
    -0.06
     kde
    -0.06
     pseud
    -0.06
     psyched
    -0.06
    ulative
    -0.06
     lớn
    -0.06
     shotgun
    -0.06
     เขต
    -0.06
    POSITIVE LOGITS
    .FileInputStream
    0.06
    �
    0.06
    .Files
    0.06
    _SUB
    0.06
     pNode
    0.06
    BufferData
    0.06
    (GET
    0.06
    -fill
    0.06
     PayPal
    0.06
    .orange
    0.05
    Act Density 0.022%

    No Known Activations