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

    Neuronpedia

    INDEX
    Explanations

    hidden, lurking, unknown

    np_max-act · gemini-2.0-flash

    phrases indicating specific phobias or fears experienced by individuals.

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

    This neuron detects numeric tokens (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     муз
    -0.07
    723
    -0.07
    لب
    -0.07
     portrays
    -0.07
    mentions
    -0.06
    mony
    -0.06
    imony
    -0.06
    otland
    -0.06
     backed
    -0.06
    ships
    -0.06
    POSITIVE LOGITS
     persu
    0.07
     lurking
    0.06
     만족
    0.06
    лення
    0.06
    Adapter
    0.06
    ToLeft
    0.06
     benign
    0.06
    .onload
    0.06
    ΕΡ
    0.06
     Miguel
    0.06
    Act Density 0.020%

    No Known Activations