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

    Neuronpedia

    INDEX
    Explanations

    percentage

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens and related units specifying training durations, distances, intensities, or other workout parameters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    eo
    -0.07
    sprites
    -0.07
    रण
    -0.07
    átní
    -0.06
    っち
    -0.06
    lio
    -0.06
     Bet
    -0.06
    flatMap
    -0.06
     apolog
    -0.06
     cit
    -0.06
    POSITIVE LOGITS
    Public
    0.08
     FontWeight
    0.07
    ký
    0.07
     Senior
    0.07
    871
    0.06
     Convenient
    0.06
     lịch
    0.06
     Tüm
    0.06
     combating
    0.06
     činnost
    0.06
    Act Density 0.009%

    No Known Activations