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

    Neuronpedia

    INDEX
    Explanations

    todo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,content
    -0.07
     Gul
    -0.07
    uctor
    -0.06
    값
    -0.06
    後の
    -0.06
     이것
    -0.06
     Reef
    -0.06
    Kernel
    -0.06
     arteries
    -0.06
     JPanel
    -0.06
    POSITIVE LOGITS
     todo
    0.13
    todo
    0.13
     Todo
    0.12
    Todo
    0.11
    tod
    0.10
    /todo
    0.09
    .todo
    0.08
    todos
    0.08
    odo
    0.08
    (todo
    0.08
    Act Density 0.005%

    No Known Activations