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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Merge
    -0.08
    .Tele
    -0.08
    >'+↵
    -0.07
    ехал
    -0.07
    .nextLine
    -0.07
     zostały
    -0.07
    -utils
    -0.07
    peek
    -0.07
     heg
    -0.07
    production
    -0.06
    POSITIVE LOGITS
     RA
    0.07
     embarrassing
    0.07
    GPIO
    0.07
    ASH
    0.07
     noteworthy
    0.07
    轮流
    0.07
     önemli
    0.06
    David
    0.06
    SCR
    0.06
     времени
    0.06
    Act Density 0.001%

    No Known Activations