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

    Neuronpedia

    INDEX
    Explanations

    complications arise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ని
    2.28
    ंग
    2.00
    м
    1.98
     accad
    1.97
     dunno
    1.91
    υ
    1.91
    uff
    1.89
    েইলি
    1.88
    ۰۰
    1.86
    ین
    1.81
    POSITIVE LOGITS
    ्य
    2.14
    namen
    1.92
    ation
    1.91
     وعلى
    1.88
    ాలు
    1.83
    lines
    1.78
    nije
    1.73
    pathTemplates
    1.72
    دست
    1.71
     Standardization
    1.70
    Act Density 0.018%

    No Known Activations