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

    Neuronpedia

    INDEX
    Explanations

    Rounding and floor functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    तीय
    -0.08
    ‍ക്ക
    -0.08
     playlists
    -0.08
     menem
    -0.08
    ‍ക്ക്
    -0.08
    혀
    -0.07
    იში
    -0.07
     incrível
    -0.07
     coche
    -0.07
    ğ
    -0.07
    POSITIVE LOGITS
    eps
    0.09
     eps
    0.08
    _eps
    0.08
    orst
    0.08
     Constraints
    0.07
     légèrement
    0.07
     Wisdom
    0.07
     epsilon
    0.07
     sof
    0.07
     subj
    0.07
    Act Density 0.007%

    No Known Activations