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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions/legal jargon

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially floating‐point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     setError
    -0.07
     Nex
    -0.07
    .UPDATE
    -0.06
    �
    -0.06
     protested
    -0.06
     vydání
    -0.06
     regulator
    -0.06
     demand
    -0.06
     parish
    -0.06
     atau
    -0.06
    POSITIVE LOGITS
     explain
    0.06
    eref
    0.06
    уди
    0.06
    rought
    0.06
    еліг
    0.06
     ऐ
    0.06
    clear
    0.06
     jas
    0.06
    _playlist
    0.06
    .getLongitude
    0.06
    Act Density 0.393%

    No Known Activations