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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron detects numerical tokens—especially decimal figures and other number strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    329
    -0.07
     lao
    -0.07
    ）↵↵
    -0.06
    Mismatch
    -0.06
     Provincial
    -0.06
    ステ
    -0.06
     Česko
    -0.06
     잠
    -0.06
     Pamela
    -0.06
    “At
    -0.06
    POSITIVE LOGITS
    .can
    0.07
    /&
    0.07
     يد
    0.06
    -Origin
    0.06
     achievements
    0.06
    .platform
    0.06
     LGPL
    0.06
     prize
    0.06
     meilleur
    0.06
    grab
    0.06
    Act Density 0.093%

    No Known Activations