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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is activated by numeric tokens (especially decimal or digit strings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    빠
    -0.07
    made
    -0.07
    .dex
    -0.06
     decks
    -0.06
     ghi
    -0.06
    证明
    -0.06
    _confirm
    -0.06
    الأ
    -0.06
    คว
    -0.06
    结
    -0.06
    POSITIVE LOGITS
    �
    0.07
     Flint
    0.06
     �
    0.06
     Events
    0.06
    :bg
    0.06
    *>
    0.06
     οπο
    0.06
     EU
    0.06
     spine
    0.06
    (BigDecimal
    0.06
    Act Density 0.035%

    No Known Activations