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

    Neuronpedia

    INDEX
    Explanations

    INATION

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens—especially floating‐point literals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     спрос
    -0.07
    ——
    -0.06
    ことも
    -0.06
     bourgeoisie
    -0.06
    朗
    -0.06
    ظ
    -0.06
    kie
    -0.06
    ---
    -0.06
    shape
    -0.06
    одерж
    -0.06
    POSITIVE LOGITS
    .ds
    0.07
     ман
    0.07
    DST
    0.07
     RPG
    0.06
     automatic
    0.06
     Chic
    0.06
    localStorage
    0.06
     mensen
    0.06
     Poz
    0.06
     mobil
    0.06
    Act Density 0.001%

    No Known Activations