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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    富民
    -0.08
    修补
    -0.07
    交融
    -0.07
     tytuł
    -0.07
    itizer
    -0.07
    بذل
    -0.07
    적인
    -0.07
     për
    -0.07
     Profiles
    -0.07
    瘀
    -0.07
    POSITIVE LOGITS
    DECL
    0.07
    Who
    0.07
     CI
    0.07
    热闹
    0.07
    K
    0.07
     dared
    0.06
    漫长
    0.06
    .sorted
    0.06
     waited
    0.06
    -c
    0.06
    Act Density 0.001%

    No Known Activations