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

    Neuronpedia

    INDEX
    Explanations

    understanding you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    También
    0.50
    ያንዳ
    0.46
     simplifié
    0.46
    ствуйте
    0.45
    ôté
    0.45
     simplification
    0.44
    égation
    0.43
    стіше
    0.43
    ต่
    0.42
     resultContent
    0.42
    POSITIVE LOGITS
     ();
    0.51
    can
    0.48
     da
    0.42
     Quebec
    0.42
     আবিষ্কার
    0.42
     can
    0.41
    an
    0.41
    scr
    0.40
    shel
    0.40
     Catalunya
    0.39
    Act Density 0.002%

    No Known Activations