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

    Neuronpedia

    INDEX
    Explanations

    hormone benefits and adherence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    finaly
    0.83
    ㇂
    0.83
    ктери
    0.83
     garages
    0.79
     giriyoruz
    0.77
    czki
    0.77
     сро
    0.76
    ју
    0.75
     الزاويه
    0.75
     workstations
    0.74
    POSITIVE LOGITS
    Making
    0.74
    %
    0.72
    チラ
    0.69
     grated
    0.66
     😊
    0.65
    $
    0.64
    Map
    0.64
    é
    0.63
    긋
    0.63
    uce
    0.62
    Act Density 0.000%

    No Known Activations