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

    Neuronpedia

    INDEX
    Explanations

    Code, times, dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    或许是
    -0.08
    marketing
    -0.07
     pozostał
    -0.07
    (Scene
    -0.07
    .sg
    -0.07
    などが
    -0.06
    让用户
    -0.06
    ="?
    -0.06
     такое
    -0.06
     bloss
    -0.06
    POSITIVE LOGITS
    -client
    0.07
    }}↵↵
    0.07
    precio
    0.07
     DJs
    0.06
     ساعة
    0.06
     sponsoring
    0.06
    هواتف
    0.06
    Resolver
    0.06
     uptime
    0.06
     условия
    0.06
    Act Density 0.001%

    No Known Activations