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

    Neuronpedia

    INDEX
    Explanations

    you can / cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.41
    াম
    0.29
    a
    0.29
    ീ
    0.29
    z
    0.28
    ম্
    0.28
    an
    0.28
    m
    0.28
    AMP
    0.27
    p
    0.26
    POSITIVE LOGITS
     can
    0.34
     τόσο
    0.32
     be
    0.31
     כ
    0.30
     was
    0.30
     cried
    0.29
     ח
    0.29
     đầu
    0.29
     que
    0.28
     has
    0.28
    Act Density 1.207%

    No Known Activations