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

    Neuronpedia

    INDEX
    Explanations

    S3 object model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inguishing
    0.40
     C
    0.38
    Ц
    0.36
     Verdict
    0.35
    分辨率
    0.35
     Elite
    0.35
    ర్‌లో
    0.35
    真实的
    0.35
    魉
    0.35
    执行
    0.34
    POSITIVE LOGITS
    خلي
    0.47
    gos
    0.45
    ROSS
    0.44
     nowy
    0.43
    釀
    0.43
    <0xA3>
    0.41
     newly
    0.41
    gios
    0.41
    OPES
    0.40
    ಕ್ಸ್
    0.39
    Act Density 0.000%

    No Known Activations