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

    Neuronpedia

    INDEX
    Explanations

    Go, Pi, Elo, Raeya

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ü
    1.01
    ש
    1.01
     to
    0.89
    ă
    0.81
    ش
    0.79
     alkan
    0.79
     I
    0.77
     O
    0.77
    د
    0.77
    ა
    0.76
    POSITIVE LOGITS
    ’,
    0.69
    ﻭ
    0.68
     bombshell
    0.63
    ’;
    0.63
    ’
    0.63
    ită
    0.61
    یده
    0.61
     rápid
    0.61
    ന്മാ
    0.61
     trembling
    0.59
    Act Density 0.054%

    No Known Activations