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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :]
    -0.06
    sprites
    -0.06
     filib
    -0.06
    產
    -0.06
     �
    -0.06
     ضر
    -0.06
     breadcrumbs
    -0.06
    bolt
    -0.06
     Busty
    -0.06
     supervised
    -0.05
    POSITIVE LOGITS
     Wine
    0.07
    (Size
    0.07
    _Device
    0.07
    ^
    0.07
     upset
    0.06
    λέ
    0.06
     nemoc
    0.06
     Volunteer
    0.06
    isa
    0.06
     berg
    0.06
    Act Density 0.000%

    No Known Activations