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

    Neuronpedia

    INDEX
    Explanations

    performance

    np_max-act · gemini-2.0-flash

    The neuron detects words referring to a product’s effectiveness (e.g. “effective,” “effectiveness”) and related quality descriptors.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     grill
    -0.07
     ra
    -0.07
    perience
    -0.06
    enschaft
    -0.06
     buf
    -0.06
     apoptosis
    -0.06
    URLException
    -0.06
    nnen
    -0.06
    不足
    -0.06
    elapsed
    -0.06
    POSITIVE LOGITS
     روسی
    0.07
     mastur
    0.07
    (D
    0.07
     seiz
    0.07
     takeover
    0.06
    oud
    0.06
     intense
    0.06
     digital
    0.06
     transparent
    0.06
    حت
    0.06
    Act Density 0.026%

    No Known Activations