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

    Neuronpedia

    INDEX
    Explanations

    biased decisions or incorrect lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    บัน
    0.44
    妤
    0.40
    荽
    0.39
    зидент
    0.39
     문
    0.38
     активно
    0.38
    Texto
    0.38
    法轮
    0.38
    校园
    0.37
    UnifiedTopology
    0.36
    POSITIVE LOGITS
    os
    0.54
    you
    0.52
    required
    0.48
     needed
    0.47
    we
    0.47
    creating
    0.45
    zo
    0.45
    candidate
    0.45
    which
    0.44
    final
    0.44
    Act Density 0.002%

    No Known Activations