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

    Neuronpedia

    INDEX
    Explanations

    numbers in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delusions
    0.48
    们
    0.47
     podido
    0.47
    簡単な
    0.47
     verstehen
    0.47
     misconceptions
    0.47
     thawed
    0.47
     pests
    0.46
    されない
    0.46
    牥
    0.46
    POSITIVE LOGITS
    b
    0.63
    which
    0.57
    m
    0.57
    in
    0.54
    g
    0.52
    ʿ
    0.52
    なども
    0.52
    d
    0.50
    <i>
    0.49
    to
    0.49
    Act Density 0.011%

    No Known Activations