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

    Neuronpedia

    INDEX
    Explanations

    google Bard AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    优化
    0.47
    优
    0.46
    ਧੀ
    0.41
    STREAM
    0.39
    োগ্য
    0.38
     Drug
    0.38
     optimizations
    0.38
    㛲
    0.38
    drug
    0.38
    巧克力
    0.37
    POSITIVE LOGITS
    Bard
    0.63
     Bard
    0.61
     bard
    0.59
     Bord
    0.52
    bard
    0.49
    bord
    0.44
     loạn
    0.43
     Borden
    0.43
    stown
    0.40
    Throws
    0.39
    Act Density 0.004%

    No Known Activations