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

    Neuronpedia

    INDEX
    Explanations

    Sexual activity/arousal

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens—it does not detect any pattern in these examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     千
    -0.07
     Facilities
    -0.07
    utters
    -0.06
     conversion
    -0.06
    Constant
    -0.06
     todd
    -0.06
     Mk
    -0.06
    "<<
    -0.06
     Super
    -0.06
     subscriber
    -0.06
    POSITIVE LOGITS
    )(_
    0.07
    hawks
    0.07
    .be
    0.07
     وغير
    0.07
    ]=(
    0.07
     ages
    0.07
     QtGui
    0.06
     remote
    0.06
     Prahy
    0.06
    )._
    0.06
    Act Density 0.014%

    No Known Activations