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

    Neuronpedia

    INDEX
    Explanations

    Math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⏮
    -0.07
    麋
    -0.07
    뮹
    -0.07
     sanctuary
    -0.06
     componentDid
    -0.06
    ┭
    -0.06
     Sentry
    -0.06
    vehicles
    -0.06
     Pell
    -0.06
    gravity
    -0.06
    POSITIVE LOGITS
    학
    0.08
     whistle
    0.08
    防线
    0.08
    𝒂
    0.07
     optimize
    0.07
     pedals
    0.07
    𝒃
    0.07
     програм
    0.07
    �
    0.07
    া
    0.06
    Act Density 0.001%

    No Known Activations