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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ющего
    -0.07
    瀬
    -0.07
     jlong
    -0.07
     Edinburgh
    -0.06
    Gün
    -0.06
     Jenner
    -0.06
    enary
    -0.06
    imizeBox
    -0.06
    โอ
    -0.06
     soar
    -0.06
    POSITIVE LOGITS
     careful
    0.07
     Quiet
    0.07
    /account
    0.07
    .met
    0.06
    .heroku
    0.06
    .mark
    0.06
    oubles
    0.06
    rum
    0.06
     сход
    0.06
    NASA
    0.06
    Act Density 0.014%

    No Known Activations