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

    Neuronpedia

    INDEX
    Explanations

    ternary diagrams, Transfer Function, cross-sell email

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    larında
    1.44
    larına
    1.27
     Besonders
    1.22
    что
    1.21
    RESSION
    1.20
    pected
    1.17
    勖
    1.17
    that
    1.16
    larından
    1.16
     cualquiera
    1.16
    POSITIVE LOGITS
    ’
    1.46
    age
    1.42
    ↵
    1.38
    ित
    1.34
    ell
    1.32
    ik
    1.31
    ร
    1.31
    ^{
    1.28
     of
    1.27
    री
    1.27
    Act Density 0.000%

    No Known Activations