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

    Neuronpedia

    INDEX
    Explanations

    superb, elegant, sophisticated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াবণ
    0.44
     זי
    0.42
     incentivize
    0.40
    ̞
    0.40
     автора
    0.39
     ८
    0.39
     stronie
    0.39
    ٹا
    0.38
    leme
    0.38
     реально
    0.38
    POSITIVE LOGITS
     superb
    0.46
     elegant
    0.42
     Simultaneous
    0.42
     wonderful
    0.41
    ရိ
    0.40
     великолеп
    0.40
     sophisticated
    0.39
     magnificent
    0.39
     unified
    0.39
     bleached
    0.39
    Act Density 0.003%

    No Known Activations