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

    Neuronpedia

    INDEX
    Explanations

    metal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    likelihood
    -0.07
    odynamics
    -0.07
     challenged
    -0.07
    าระ
    -0.06
    _Con
    -0.06
     inclination
    -0.06
     Croatian
    -0.06
    ibility
    -0.06
    AffineTransform
    -0.06
     Kend
    -0.06
    POSITIVE LOGITS
     [=[
    0.07
    聽
    0.07
    ;font
    0.06
    <img
    0.06
    localObject
    0.06
     pornography
    0.06
    typeparam
    0.06
    鏡
    0.06
    angles
    0.06
    ~=
    0.06
    Act Density 0.001%

    No Known Activations