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

    Neuronpedia

    INDEX
    Explanations

    translations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (["
    -0.06
    nam
    -0.06
    <Object
    -0.06
    сяг
    -0.06
    apiro
    -0.06
     mph
    -0.06
    esiyle
    -0.06
    يلا
    -0.06
    adds
    -0.06
    carbon
    -0.06
    POSITIVE LOGITS
     luckily
    0.06
    务
    0.06
     sockets
    0.06
    (sock
    0.06
    俄
    0.06
    ,password
    0.06
    Calling
    0.06
    (cancel
    0.06
     grappling
    0.06
    .radio
    0.06
    Act Density 0.032%

    No Known Activations