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

    Neuronpedia

    INDEX
    Explanations

    pl, à, 0, cdc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ανθρώ
    0.29
     ergodic
    0.29
     éviter
    0.28
     phrasing
    0.27
    ercase
    0.26
     prä
    0.26
    identify
    0.26
     ず
    0.26
     worded
    0.26
     insbesondere
    0.25
    POSITIVE LOGITS
    वहीं
    0.31
     वहीं
    0.28
    oya
    0.27
     এছাড়া
    0.27
     Poole
    0.26
     kasnije
    0.26
    近年
    0.25
    ilya
    0.25
    Similarly
    0.25
    এছাড়া
    0.25
    Act Density 0.292%

    No Known Activations