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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     програми
    -0.06
    (ra
    -0.06
    IsNull
    -0.06
    ’na
    -0.06
    ῖ
    -0.06
     grd
    -0.06
     बय
    -0.06
    -description
    -0.06
    ahy
    -0.06
    _flag
    -0.06
    POSITIVE LOGITS
     Tell
    0.07
    tos
    0.07
    elf
    0.07
     certainly
    0.06
    )(((
    0.06
     преж
    0.06
    .Small
    0.06
    Verifier
    0.06
     Rosenberg
    0.06
     seems
    0.06
    Act Density 0.015%

    No Known Activations