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

    Neuronpedia

    INDEX
    Explanations

    Hallucinogens and psychedelics

    np_max-act · gemini-2.0-flash

    content related to categories of unsafe and inappropriate material, particularly concerning sexual content and drug references.

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

    The neuron activates on mentions of hallucinogenic drug terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lint
    -0.08
     wires
    -0.07
     функци
    -0.07
     logout
    -0.07
    р
    -0.07
     Manager
    -0.07
    ์)
    -0.06
    "In
    -0.06
    ツ
    -0.06
    rikes
    -0.06
    POSITIVE LOGITS
    하는데
    0.07
     psychedelic
    0.06
    (ARG
    0.06
     els
    0.06
     tuned
    0.06
     offen
    0.06
    umbling
    0.06
    (sent
    0.06
     Qing
    0.06
     görül
    0.06
    Act Density 0.002%

    No Known Activations