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

    Neuronpedia

    INDEX
    Explanations

    tarinas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.80
    ीय
    1.69
    ことになる
    1.66
    ことです
    1.65
    మీ
    1.63
    ी
    1.61
    ɳ
    1.56
     lapse
    1.54
    trajectory
    1.51
    आत
    1.50
    POSITIVE LOGITS
    ൂ
    1.59
     svega
    1.50
     conhece
    1.47
    เท้า
    1.47
    of
    1.45
    oreet
    1.45
    ată
    1.42
    liest
    1.41
    んだ
    1.40
     siquiera
    1.40
    Act Density 0.000%

    No Known Activations