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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash

    This neuron responds to quantitative technical details—numbers, units, and specification terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .bz
    -0.07
     �
    -0.06
    ення
    -0.06
     Tub
    -0.06
     الك
    -0.06
    FIELD
    -0.06
    位置
    -0.06
     Lans
    -0.06
    ुँ
    -0.06
     Belly
    -0.06
    POSITIVE LOGITS
    طقة
    0.07
    -note
    0.06
    _Widget
    0.06
    !).↵↵
    0.06
    svg
    0.06
    remove
    0.06
     trimmed
    0.06
     Functor
    0.06
     protected
    0.06
    Pressed
    0.06
    Act Density 0.201%

    No Known Activations