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

    Neuronpedia

    INDEX
    Explanations

    Simplicity and appearance

    np_max-act · gemini-2.0-flash

    content related to physical sensations or actions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is detecting floating‐point number tokens (i.e. decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    یین
    -0.07
    akin
    -0.06
     Towers
    -0.06
     Vaccine
    -0.06
    وبی
    -0.06
     EEG
    -0.06
     nurs
    -0.06
     Swim
    -0.06
    /Game
    -0.06
     infections
    -0.06
    POSITIVE LOGITS
    _barang
    0.06
    -dollar
    0.06
    şı
    0.06
    کاران
    0.06
     معل
    0.06
    coh
    0.06
    .querySelectorAll
    0.06
    fos
    0.06
     Kasich
    0.06
    owego
    0.06
    Act Density 0.148%

    No Known Activations