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

    Neuronpedia

    INDEX
    Explanations

    code documentation or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    αν
    0.51
    ada
    0.47
     Thánh
    0.46
    ę
    0.43
    ło
    0.42
     συνεχ
    0.42
    emente
    0.41
    ão
    0.41
    aba
    0.41
    ätzlich
    0.41
    POSITIVE LOGITS
     замет
    0.51
    Investors
    0.48
     importers
    0.46
     मांग
    0.45
    July
    0.45
    лий
    0.44
    ICAN
    0.44
     enterr
    0.44
     निवेशक
    0.43
    }}}$
    0.43
    Act Density 0.006%

    No Known Activations