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

    Neuronpedia

    INDEX
    Explanations

    two-digit numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric percentage expressions in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uddenly
    -0.07
    ’na
    -0.07
     headaches
    -0.06
     promise
    -0.06
     χρόνια
    -0.06
     clamp
    -0.06
    .Series
    -0.06
     também
    -0.06
     legalize
    -0.06
     будів
    -0.06
    POSITIVE LOGITS
     �
    0.07
     sentimental
    0.06
     got
    0.06
     jejichž
    0.06
    Ten
    0.06
     BIND
    0.06
     Cron
    0.06
     Gio
    0.06
     husbands
    0.06
     Scott
    0.06
    Act Density 0.028%

    No Known Activations