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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ugu
    -0.07
     五
    -0.07
     Гор
    -0.07
    -',
    -0.06
     yoğun
    -0.06
    track
    -0.06
    isters
    -0.06
     останов
    -0.06
    Specify
    -0.06
     held
    -0.06
    POSITIVE LOGITS
    (ierr
    0.06
     {↵↵↵↵
    0.06
    졌다
    0.06
    cko
    0.06
    .readInt
    0.06
     méth
    0.06
     Degrees
    0.05
    ━━━━━━━━━━━━━━━━
    0.05
     Malone
    0.05
    _SSL
    0.05
    Act Density 0.247%

    No Known Activations