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

    Neuronpedia

    INDEX
    Explanations

    new additions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Faster
    0.44
     stades
    0.43
     leit
    0.40
    cers
    0.40
    oforte
    0.39
    ♰
    0.39
    vé
    0.39
     transmis
    0.39
     stanowi
    0.39
     kaun
    0.38
    POSITIVE LOGITS
     new
    1.39
     новых
    1.39
     additions
    1.38
     새로운
    1.35
    新增
    1.34
     neuen
    1.34
     নতুন
    1.30
     nuevos
    1.28
    新的
    1.27
     nuevas
    1.26
    Act Density 0.655%

    No Known Activations