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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not respond to any text patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     xr
    -0.07
    (head
    -0.07
    鬼
    -0.07
    urv
    -0.06
     angl
    -0.06
     DataGridView
    -0.06
    rám
    -0.06
     Κά
    -0.06
     adb
    -0.06
     exhibitions
    -0.06
    POSITIVE LOGITS
    Lou
    0.06
    tipo
    0.06
     мяс
    0.06
     GetType
    0.06
    ooting
    0.06
    illing
    0.06
    -middle
    0.06
    ProcessEvent
    0.06
     üst
    0.06
    optimize
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.