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

    Neuronpedia

    INDEX
    Explanations

    URLs and citations in research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),\
    0.80
     thous
    0.76
     lacs
    0.74
     togel
    0.74
     auch
    0.74
     லட்சம்
    0.70
    __);
    0.70
     тыс
    0.69
     sundry
    0.69
    Brien
    0.69
    POSITIVE LOGITS
    aley
    0.76
    ᚗ
    0.66
    ambahan
    0.65
     pâte
    0.65
     empresarios
    0.64
    ποίη
    0.63
    akkhand
    0.63
     있어서
    0.63
    Advances
    0.63
    memory
    0.63
    Act Density 0.001%

    No Known Activations