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

    Neuronpedia

    INDEX
    Explanations

    data processing

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens—especially decimal numbers—within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aks
    -0.07
    ‌ترین
    -0.06
    73
    -0.06
    .inline
    -0.06
     //↵↵
    -0.06
    (rec
    -0.06
    )||
    -0.05
    ancies
    -0.05
    >{@
    -0.05
     συγκ
    -0.05
    POSITIVE LOGITS
    Typography
    0.06
    AllWindows
    0.06
     Realm
    0.06
    .opt
    0.06
     glGet
    0.06
     anale
    0.06
     nouvelles
    0.06
     Adventure
    0.06
     Leipzig
    0.06
     Covers
    0.06
    Act Density 0.033%

    No Known Activations