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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric expressions—digits, measurements, quantities, and related units.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     discouraged
    -0.07
    ours
    -0.06
     earth
    -0.06
     Mang
    -0.06
     Pinterest
    -0.06
    _PARAMETERS
    -0.06
     grapes
    -0.06
    ica
    -0.06
     colourful
    -0.06
     dày
    -0.06
    POSITIVE LOGITS
     aspirations
    0.06
     sadece
    0.06
    java
    0.06
    โ
    0.06
    NavItem
    0.06
    ModelIndex
    0.06
    _hat
    0.06
    Sphere
    0.06
     nós
    0.06
     Yii
    0.06
    Act Density 0.066%

    No Known Activations