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

    Neuronpedia

    INDEX
    Explanations

    SVG and HTML elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.52
    er
    0.50
    ed
    0.49
    ির
    0.45
    కు
    0.43
    el
    0.42
    ,
    0.41
    ার
    0.39
    ↵↵
    0.39
    '
    0.39
    POSITIVE LOGITS
     be
    0.51
    ב
    0.47
     Ο
    0.42
     up
    0.41
    б
    0.41
     داشت
    0.40
    ров
    0.40
    ق
    0.39
     ၂
    0.38
    unate
    0.36
    Act Density 0.029%

    No Known Activations