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

    Neuronpedia

    INDEX
    Explanations

    going beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rceil
    0.68
    حه
    0.68
    }))$
    0.64
    matchCondition
    0.63
     valam
    0.62
    }=(
    0.62
    ؕ
    0.61
    }|$
    0.61
    驀
    0.61
     getpath
    0.61
    POSITIVE LOGITS
     beyond
    5.52
     Beyond
    4.98
    beyond
    4.88
    Beyond
    4.85
     além
    2.98
     besides
    2.88
     aside
    2.68
     помимо
    2.61
    之外
    2.58
    Besides
    2.49
    Act Density 1.220%

    No Known Activations