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

    Neuronpedia

    INDEX
    Explanations

    death and violence

    np_max-act · gemini-2.0-flash

    The neuron activates on language describing looting, scavenging, or collecting items (e.g. “loot,” “scavenge,” “give,” “enemy defeated”) after combat.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ्यत
    -0.08
     Wenger
    -0.07
     espionage
    -0.07
     внимание
    -0.07
     chocol
    -0.07
     restaur
    -0.06
    喜欢
    -0.06
     Griffin
    -0.06
    خل
    -0.06
     Ấ
    -0.06
    POSITIVE LOGITS
    approximately
    0.08
     figura
    0.07
    _figure
    0.07
    :Boolean
    0.06
     seksi
    0.06
     ModelAndView
    0.06
    doch
    0.06
    hipster
    0.06
    _Time
    0.06
     ListViewItem
    0.06
    Act Density 0.008%

    No Known Activations