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

    Neuronpedia

    INDEX
    Explanations

    end of sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    radas
    0.38
     말미암아
    0.38
    venty
    0.37
     henceforth
    0.37
    rtel
    0.36
     Kanada
    0.36
    utel
    0.35
     ቀላል
    0.35
    yrıca
    0.35
     ओह
    0.35
    POSITIVE LOGITS
     यानी
    0.51
     অর্থাৎ
    0.49
     тобто
    0.48
    也就是
    0.45
    অর্থাৎ
    0.44
     but
    0.43
    つまり
    0.43
    也就是说
    0.42
    เลย
    0.42
     nhưng
    0.41
    Act Density 0.007%

    No Known Activations