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

    Neuronpedia

    INDEX
    Explanations

    storytelling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perceptual
    0.39
     cognitive
    0.38
     prioritize
    0.38
     introspection
    0.38
    ifestyle
    0.37
    ifiques
    0.37
    ivel
    0.37
    señ
    0.37
     prioritise
    0.37
    assara
    0.37
    POSITIVE LOGITS
     unfolding
    1.93
     unfold
    1.91
     unfolds
    1.84
     unfolded
    1.77
    展開
    1.33
    展开
    1.31
     dérou
    1.15
     펼
    1.15
    펼
    1.02
     raccont
    1.00
    Act Density 0.068%

    No Known Activations