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

    Neuronpedia

    INDEX
    Explanations

    scientists, researchers, residents, locals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    0.88
    of
    0.76
    ?
    0.74
    أ
    0.74
    會
    0.71
    to
    0.70
    بر
    0.70
    ur
    0.69
     on
    0.68
    性
    0.67
    POSITIVE LOGITS
    li
    0.73
    liğini
    0.65
    ៤
    0.62
    lerce
    0.62
    ៩
    0.59
     theologians
    0.59
    ih
    0.58
    ㅋㅋ
    0.57
    ли
    0.57
     மத்தியில்
    0.57
    Act Density 0.263%

    No Known Activations