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

    Neuronpedia

    INDEX
    Explanations

    become

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens, especially decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kas
    -0.07
     best
    -0.07
    illian
    -0.07
    54
    -0.07
    izz
    -0.07
     itch
    -0.07
     likes
    -0.06
     Hass
    -0.06
    first
    -0.06
    Traversal
    -0.06
    POSITIVE LOGITS
     پیدا
    0.07
     λεπ
    0.07
    вано
    0.07
    .setIcon
    0.06
    .Utc
    0.06
     انتقال
    0.06
    Это
    0.06
     adını
    0.06
    .strftime
    0.06
     Tato
    0.06
    Act Density 0.029%

    No Known Activations