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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /controllers
    -0.07
    }],↵
    -0.07
     reservations
    -0.07
    reach
    -0.07
     >
↵
    -0.07
    testCase
    -0.07
    URAL
    -0.07
    脲
    -0.07
    <location
    -0.07
     League
    -0.06
    POSITIVE LOGITS
    从而
    0.07
    �
    0.06
    まさ
    0.06
    …..
    0.06
     вели
    0.06
    甚么
    0.06
     لم
    0.06
     ogłos
    0.06
    칫
    0.06
    uis
    0.06
    Act Density 0.268%

    No Known Activations