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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    របស់
    0.39
     отно
    0.37
    oddsidemargin
    0.36
    応用
    0.36
    ह्न
    0.35
     cis
    0.34
     نقصان
    0.34
    នៃ
    0.33
    หน้า
    0.33
    ่อย
    0.33
    POSITIVE LOGITS
     participa
    0.41
     separates
    0.38
     latach
    0.38
    alami
    0.38
    راج
    0.38
     TA
    0.37
    separ
    0.37
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
    }$:
    0.36
     initiates
    0.36
    Act Density 0.001%

    No Known Activations