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

    Neuronpedia

    INDEX
    Explanations

    words ending in us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    -0.14
    tl
    -0.14
    tır
    -0.13
    tion
    -0.13
    tap
    -0.13
    ts
    -0.13
    tx
    -0.13
    ta
    -0.13
    ture
    -0.13
    ت
    -0.13
    POSITIVE LOGITS
    ness
    0.33
    (es
    0.31
    ses
    0.31
    '
    0.26
    ’;
    0.26
    phere
    0.23
    es
    0.22
    sing
    0.20
    sss
    0.19
    aurus
    0.19
    Act Density 0.197%

    No Known Activations