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

    Neuronpedia

    INDEX
    Explanations

    existing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HW
    -0.06
    Displays
    -0.06
    .Enqueue
    -0.06
     tặng
    -0.06
    енд
    -0.06
     이어
    -0.05
    .AddModelError
    -0.05
    CAST
    -0.05
     magnets
    -0.05
     AF
    -0.05
    POSITIVE LOGITS
     purple
    0.08
     fire
    0.07
     `↵
    0.07
    .stock
    0.07
     servi
    0.06
    )!↵
    0.06
    ure
    0.06
    Pu
    0.06
    。”↵↵
    0.06
    Pure
    0.06
    Act Density 0.000%

    No Known Activations