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

    Neuronpedia

    INDEX
    Explanations

    Scents/smells

    np_max-act · gemini-2.0-flash

    The neuron is looking for scent-related descriptors—words that evoke aromas or fragrances.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    自分
    -0.06
    _slots
    -0.06
    OLE
    -0.06
    那些
    -0.06
     Thank
    -0.06
    Teen
    -0.06
    ارا
    -0.06
    حم
    -0.06
     gramm
    -0.06
    时候
    -0.06
    POSITIVE LOGITS
     PartialEq
    0.07
    .clearRect
    0.07
     devast
    0.06
    JT
    0.06
    /container
    0.06
     burnt
    0.06
     regional
    0.06
    acente
    0.06
    claims
    0.06
     synergy
    0.06
    Act Density 0.089%

    No Known Activations