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

    Neuronpedia

    INDEX
    Explanations

    business listings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {|
    -0.08
    []);↵
    -0.07
    大きい
    -0.07
    !'↵
    -0.07
     declared
    -0.07
    ߎ
    -0.07
     ];
↵
    -0.07
    Elite
    -0.06
    电
    -0.06
    ()]↵
    -0.06
    POSITIVE LOGITS
     accordion
    0.08
    ogenesis
    0.08
    QUENCY
    0.08
     nhiệm
    0.08
    没法
    0.08
     fps
    0.08
     hammer
    0.07
    臼
    0.07
     vực
    0.07
     sistem
    0.07
    Act Density 0.060%

    No Known Activations