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

    Neuronpedia

    INDEX
    Explanations

    digit

    np_max-act · gemini-2.0-flash

    This neuron flags occurrences of the word “digit.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     march
    -0.07
     Awareness
    -0.07
    Wall
    -0.07
     نمی
    -0.07
     moms
    -0.07
     awareness
    -0.06
    18
    -0.06
     Accum
    -0.06
     Patio
    -0.06
     ❤
    -0.06
    POSITIVE LOGITS
     digits
    0.10
    _digits
    0.08
     dign
    0.07
     digging
    0.07
     digit
    0.07
    چی
    0.07
    SCRIPT
    0.07
    digit
    0.07
    .Down
    0.07
     divert
    0.07
    Act Density 0.006%

    No Known Activations