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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron detects numerical quantities—numbers (often with units or measures) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    descriptions of historical events and figures, particularly those related to sports and cultural activities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pole
    -0.07
    Controls
    -0.07
    658
    -0.06
    'e
    -0.06
    ANS
    -0.06
    .peer
    -0.06
     Panda
    -0.06
    ITA
    -0.06
     Forced
    -0.06
    ans
    -0.06
    POSITIVE LOGITS
     artillery
    0.07
    +'\
    0.06
    =img
    0.06
     atr
    0.06
    _cor
    0.06
     عملیات
    0.06
     замен
    0.06
     notably
    0.06
    /Typography
    0.06
    ?\
    0.06
    Act Density 0.080%

    No Known Activations