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

    Neuronpedia

    INDEX
    Explanations

    Code and mixed language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ÑģÑĤвенно
    -0.28
    è¶Ĭæĺ¯
    -0.28
    åºĨ幸
    -0.27
    æīĢ以说
    -0.27
    ”),
    -0.26
    etimes
    -0.25
    ”;
    -0.25
    .";
    -0.25
    /AP
    -0.25
     ÑĤоÑĤ
    -0.25
    POSITIVE LOGITS
    uan
    0.28
    ancode
    0.26
    pee
    0.26
    tá
    0.26
    ignite
    0.25
    åijĬåĪ«
    0.24
    hi
    0.24
    kind
    0.24
     nir
    0.24
    æ³¥
    0.24
    Act Density 18.295%

    No Known Activations