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

    Neuronpedia

    INDEX
    Explanations

    system logs

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numbers (floating-point values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    див
    -0.08
     depression
    -0.07
    헤
    -0.07
    Seed
    -0.07
     persuaded
    -0.07
    Distribution
    -0.07
     flu
    -0.07
     основном
    -0.06
    ↵↵↵↵↵↵↵↵↵
    -0.06
    토
    -0.06
    POSITIVE LOGITS
     speaking
    0.07
     classname
    0.06
    WEB
    0.06
     Ki
    0.06
    _ABS
    0.06
     AUX
    0.06
     ο
    0.06
    registr
    0.06
     八
    0.06
     AVG
    0.06
    Act Density 0.035%

    No Known Activations