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

    Neuronpedia

    INDEX
    Explanations

    industry

    np_max-act · gemini-2.0-flash

    The neuron flags numeric tokens—especially floating‐point numbers (e.g. “0.218505859375”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cous
    -0.07
     bloss
    -0.06
    Node
    -0.06
    Document
    -0.06
     Assets
    -0.06
    lerdir
    -0.06
     Tud
    -0.06
    UMP
    -0.06
     Junior
    -0.06
     £
    -0.06
    POSITIVE LOGITS
     massasje
    0.07
     عاش
    0.06
     tamil
    0.06
    .orm
    0.06
     datas
    0.06
    (simp
    0.06
     pprint
    0.06
    ，它
    0.06
     أكبر
    0.06
    \GeneratedValue
    0.06
    Act Density 0.020%

    No Known Activations