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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KUR
    -0.06
     wicht
    -0.06
     Reception
    -0.06
    unga
    -0.06
     إل
    -0.06
     intval
    -0.06
    .viewmodel
    -0.05
     uom
    -0.05
    SpecWarn
    -0.05
     конструкции
    -0.05
    POSITIVE LOGITS
     Κα
    0.07
    ฝ
    0.07
     costing
    0.07
     york
    0.07
     tts
    0.06
     تهران
    0.06
     πα
    0.06
    siblings
    0.06
     bağır
    0.06
    銀行
    0.06
    Act Density 0.001%

    No Known Activations