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

    Neuronpedia

    INDEX
    Explanations

    elements related to technical specifications and measurements

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

    small quantities or low degrees

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects numeric expressions—numbers, measurements, and decimal/percentage-like tokens.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    asher
    -0.39
    Fine
    -0.39
     fine
    -0.39
    Hoch
    -0.37
    cèse
    -0.36
    Aro
    -0.36
    präch
    -0.35
    fine
    -0.35
    HandlerContext
    -0.35
     MainAxisSize
    -0.35
    POSITIVE LOGITS
    slightly
    0.55
     sedikit
    0.53
     Slightly
    0.52
    InputTagHelper
    0.52
    Slightly
    0.52
     Etwas
    0.50
     Slight
    0.49
    somewhat
    0.49
    最低
    0.49
     siquiera
    0.49
    Act Density 0.150%

    No Known Activations