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

    Neuronpedia

    INDEX
    Explanations

    user login information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     놀
    -0.06
    .Sound
    -0.06
     관
    -0.06
    LOWER
    -0.06
     nuestro
    -0.06
    erging
    -0.06
     eye
    -0.06
    ièrement
    -0.06
    WAR
    -0.06
    ERGY
    -0.06
    POSITIVE LOGITS
    jo
    0.07
    (Cl
    0.06
     Willi
    0.06
     fib
    0.06
     signals
    0.06
    ionale
    0.06
     Co
    0.06
    ,m
    0.06
    (square
    0.06
     doma
    0.06
    Act Density 0.009%

    No Known Activations