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

    Neuronpedia

    INDEX
    Explanations

    long double numeric types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ut
    1.53
    1.51
     commas
    1.36
    ভাবে
    1.34
    라면
    1.33
     pies
    1.32
     pancakes
    1.31
    놓
    1.29
     problems
    1.27
     adept
    1.27
    POSITIVE LOGITS
    ди
    1.37
    Figura
    1.30
    áreas
    1.30
    '
    1.25
    ússia
    1.23
    േഷ്
    1.23
     impulsar
    1.21
    ﻴ
    1.19
    enten
    1.18
    criar
    1.18
    Act Density 0.039%

    No Known Activations