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

    Neuronpedia

    INDEX
    Explanations

    often more effective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ubb
    0.40
    (`/
    0.39
    oji
    0.37
    +(\
    0.37
    นักงาน
    0.37
     Gentle
    0.36
    Chào
    0.35
    ojis
    0.35
    ットン
    0.35
    ットフォーム
    0.35
    POSITIVE LOGITS
     najlepiej
    1.44
    最好
    1.41
     best
    1.37
    最好的
    1.31
     melhor
    1.30
     najbolje
    1.30
     лучше
    1.30
     better
    1.29
     mejor
    1.28
     بهتر
    1.23
    Act Density 0.017%

    No Known Activations