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

    Neuronpedia

    INDEX
    Explanations

    introducing lists with items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ONO
    1.07
    maması
    1.02
    ുപത്രി
    0.98
    しましたが
    0.98
    ാലും
    0.98
     kiya
    0.98
    解決
    0.95
     हेल्प
    0.95
     ತ
    0.93
     membuatnya
    0.93
    POSITIVE LOGITS
     Namely
    1.07
     The
    1.01
     Slo
    0.99
     Dere
    0.95
     puisque
    0.95
     THE
    0.95
     Shortly
    0.95
     Simply
    0.95
     nagu
    0.94
     sevgili
    0.94
    Act Density 0.366%

    No Known Activations