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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salud
    -0.06
    もう
    -0.06
     roman
    -0.06
    =com
    -0.06
    (mouse
    -0.06
     bottleneck
    -0.06
    >{"
    -0.06
    中に
    -0.06
    .mas
    -0.06
    aktion
    -0.06
    POSITIVE LOGITS
    });
↵
↵
    0.07
     downloadable
    0.07
    regist
    0.06
     quantify
    0.06
     stakes
    0.06
     퍼
    0.06
     �
    0.06
    constructed
    0.06
     phê
    0.06
    %↵
    0.06
    Act Density 0.003%

    No Known Activations