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

    Neuronpedia

    INDEX
    Explanations

    Taylor Swift song titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.56
    n
    0.53
    น
    0.51
    न
    0.49
    H
    0.48
    ष्णा
    0.48
    Ca
    0.47
    G
    0.47
    F
    0.47
    X
    0.46
    POSITIVE LOGITS
    μένες
    0.46
    然而
    0.46
     வலிய
    0.45
     然而
    0.45
     LMFBR
    0.45
     Tuttavia
    0.44
     Nuest
    0.44
     vhodné
    0.44
    しましたが
    0.44
    ிகள்
    0.43
    Act Density 0.001%

    No Known Activations