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

    Neuronpedia

    INDEX
    Explanations

    personal reflections

    np_max-act · gemini-2.0-flash

    discussions of personal experiences with media or entertainment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects first-person, introspective language—especially “I” plus personal-comment verbs and reflections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    apanese
    -0.06
     Lamb
    -0.06
    構
    -0.06
     Aud
    -0.06
    :len
    -0.06
    pj
    -0.06
    �
    -0.06
    SMART
    -0.06
     flurry
    -0.06
    _play
    -0.06
    POSITIVE LOGITS
     *)
    0.08
    ruits
    0.07
     fragmentation
    0.07
    àu
    0.07
     ट
    0.07
     acknowledgment
    0.07
     Verify
    0.06
     agon
    0.06
    .de
    0.06
     implant
    0.06
    Act Density 0.110%

    No Known Activations