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

    Neuronpedia

    INDEX
    Explanations

    computers/hardware

    np_max-act · gemini-2.0-flash

    This neuron remains inactive—it does not respond to any tokens or patterns in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     FAILED
    -0.07
     aerospace
    -0.06
    .setGeometry
    -0.06
    $response
    -0.06
     localVar
    -0.06
     unrealistic
    -0.06
    itated
    -0.06
    cribing
    -0.06
     Tesla
    -0.06
     unavailable
    -0.06
    POSITIVE LOGITS
    (mem
    0.07
     DTO
    0.06
    _SEPARATOR
    0.06
     fossil
    0.06
    ,copy
    0.06
     necessário
    0.06
     DEST
    0.06
    (IP
    0.06
     SORT
    0.06
    Imagen
    0.06
    Act Density 0.168%

    No Known Activations