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

    Neuronpedia

    INDEX
    Explanations

    body parts

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming cosmetic product types or categories (e.g. body, lotion, lip, brow, eyebrow, finishing, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     taste
    -0.07
     جلو
    -0.06
     smoked
    -0.06
    _MARKER
    -0.06
    _UNIT
    -0.06
    terraform
    -0.06
    mgr
    -0.06
    _appro
    -0.06
     혼
    -0.06
    "d
    -0.06
    POSITIVE LOGITS
     airstrikes
    0.07
     strawberries
    0.07
    ใจ
    0.07
    ΩΣ
    0.07
     _
    0.06
    海外
    0.06
     profound
    0.06
    δοση
    0.06
    Sync
    0.06
     cuff
    0.06
    Act Density 0.012%

    No Known Activations