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

    Neuronpedia

    INDEX
    Explanations

    the most important or core concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৯
    2.06
    问题
    2.02
     rupam
    1.96
    р
    1.89
    Ü
    1.83
    কে
    1.80
    大规模
    1.76
    ب
    1.74
    and
    1.73
    ⁰
    1.72
    POSITIVE LOGITS
    ophylline
    1.87
    mselves
    1.73
    od
    1.68
    ocratic
    1.61
    oretically
    1.60
    യും
    1.60
     almighty
    1.48
     simplest
    1.39
    ologically
    1.39
    matic
    1.35
    Act Density 0.461%

    No Known Activations