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

    Neuronpedia

    INDEX
    Explanations

    seeing and noticing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     з
    0.33
    کو
    0.32
    io
    0.32
    ”،
    0.32
    க்கு
    0.31
     повинні
    0.31
    क
    0.30
     are
    0.30
    но
    0.30
    ﺮ
    0.29
    POSITIVE LOGITS
    et
    0.45
    t
    0.45
    r
    0.42
    d
    0.41
    m
    0.41
    ר
    0.40
    ే
    0.39
    ت
    0.39
    al
    0.38
    ر
    0.38
    Act Density 0.588%

    No Known Activations