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

    Neuronpedia

    INDEX
    Explanations

    narrative text

    np_max-act · gemini-2.0-flash

    The neuron fires on vocabulary describing violence, death, or forensic/investigative detail.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	Q
    -0.06
     optimizing
    -0.06
    ","","
    -0.06
     Aqua
    -0.06
    営
    -0.06
    	camera
    -0.06
     گونه
    -0.06
    Dia
    -0.06
    	Method
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     صالح
    0.07
    _CAT
    0.07
     PowerPoint
    0.07
    vette
    0.07
    $con
    0.06
    ント
    0.06
    .rectangle
    0.06
     Presents
    0.06
    wifi
    0.06
     pagan
    0.06
    Act Density 0.155%

    No Known Activations