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

    Neuronpedia

    INDEX
    Explanations

    leather products

    np_max-act · gemini-2.0-flash

    The neuron responds strongly to occurrences of the word “leather.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ibaba
    -0.07
     Nak
    -0.06
    ^{
    -0.06
     отмет
    -0.06
    ).__
    -0.06
    indow
    -0.06
     Surrey
    -0.06
     心
    -0.06
     urlparse
    -0.06
     Pills
    -0.06
    POSITIVE LOGITS
     leather
    0.12
     Leather
    0.11
     ch
    0.08
     tenure
    0.07
     가지
    0.07
     Vinyl
    0.07
     fj
    0.07
    leri
    0.07
    腦
    0.07
     кожи
    0.07
    Act Density 0.004%

    No Known Activations