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

    Neuronpedia

    INDEX
    Explanations

    safe container

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    shade
    1.70
     mapDispatch
    1.48
    नहीं
    1.47
    जल
    1.46
    ης
    1.45
    Tourism
    1.40
    ज
    1.37
    graduate
    1.36
    stmt
    1.36
    ă
    1.36
    POSITIVE LOGITS
    ieur
    1.42
     recht
    1.38
    arlos
    1.35
    €™
    1.34
    нага
    1.33
    oulli
    1.31
    یسی
    1.31
    ﹏
    1.30
     ----------
    1.29
    1.26
    Act Density 0.000%

    No Known Activations