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

    Neuronpedia

    INDEX
    Explanations

    `@Autowired`, `@patch`, `@app`, `@Scheduled`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    0.52
     égal
    0.46
     відповіда
    0.44
    ีก
    0.43
     jīn
    0.42
    ນ
    0.42
     ㅎ
    0.42
     brig
    0.41
     pug
    0.41
    䇢
    0.41
    POSITIVE LOGITS
    op
    0.65
    ama
    0.63
    to
    0.62
    ya
    0.61
    if
    0.59
    ia
    0.58
    frozen
    0.57
    ms
    0.56
    staticmethod
    0.56
    raw
    0.55
    Act Density 0.006%

    No Known Activations