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

    Neuronpedia

    INDEX
    Explanations

    Describing characteristics

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric expressions and quantitative measurements (numbers and decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .pixel
    -0.07
    Columns
    -0.07
    translations
    -0.07
     Favorites
    -0.06
     extracted
    -0.06
     Got
    -0.06
    imento
    -0.06
     guarantee
    -0.06
     soldier
    -0.06
     Pregn
    -0.06
    POSITIVE LOGITS
    σύ
    0.06
     حکم
    0.06
    ์ส
    0.06
    美元
    0.06
     СССР
    0.06
    水
    0.06
     Diane
    0.06
     سپ
    0.06
     �
    0.06
     trials
    0.06
    Act Density 0.134%

    No Known Activations