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

    Neuronpedia

    INDEX
    Explanations

    fitness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обработ
    -0.08
    ился
    -0.07
    ้ม
    -0.06
    ('
    -0.06
     prison
    -0.06
     Jahres
    -0.06
    /key
    -0.06
    dq
    -0.06
     Bayer
    -0.06
     real
    -0.06
    POSITIVE LOGITS
    ,v
    0.07
    (IF
    0.07
     fitness
    0.07
    Fitness
    0.07
     qs
    0.07
     backwards
    0.07
     Vim
    0.06
     bik
    0.06
     Fir
    0.06
     ABI
    0.06
    Act Density 0.002%

    No Known Activations