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

    Neuronpedia

    INDEX
    Explanations

    kind famous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.40
    infty
    0.40
     ?>">
    0.40
    悪い
    0.40
     SiO
    0.39
    <unused83>
    0.38
     ∞
    0.38
    <unused96>
    0.38
     SEA
    0.38
     >=
    0.37
    POSITIVE LOGITS
    ኰ
    0.46
    すごく
    0.45
     reminds
    0.43
     resonates
    0.42
     remarked
    0.42
     penso
    0.41
     sottoline
    0.40
     esprim
    0.40
     comment
    0.39
     আরে
    0.39
    Act Density 0.001%

    No Known Activations