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
    स
    1.09
    னர்
    1.01
    可以
    0.95
    どう
    0.92
    ுக்
    0.91
    ЗО
    0.91
    首先
    0.91
    닉
    0.89
    能
    0.89
    是
    0.88
    POSITIVE LOGITS
    tellers
    2.27
    telling
    1.77
    teller
    1.73
    ാപാ
    1.59
    tale
    1.57
     raccont
    1.55
     stories
    1.54
     tales
    1.53
     tale
    1.46
     story
    1.41
    Act Density 0.084%

    No Known Activations