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

    Neuronpedia

    INDEX
    Explanations

    next day, week, or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bits
    0.42
    retain
    0.40
    只有
    0.39
     lumbar
    0.37
     only
    0.37
    bits
    0.36
    凝
    0.36
    ారణ
    0.36
     mother
    0.36
     spe
    0.36
    POSITIVE LOGITS
     रुख
    0.43
     других
    0.40
    今後の
    0.39
     環境
    0.39
     करत
    0.38
     जानिए
    0.38
    िड
    0.38
    ▷
    0.38
     समारोह
    0.38
    amentul
    0.38
    Act Density 0.017%

    No Known Activations