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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Everett
    -0.07
    被执行人
    -0.07
     טבעי
    -0.06
     BH
    -0.06
     Paramount
    -0.06
     Potential
    -0.06
     كان
    -0.06
     Patriot
    -0.06
    ﱊ
    -0.06
    imus
    -0.06
    POSITIVE LOGITS
    "};↵↵
    0.07
     noses
    0.07
    ";
↵
    0.07
    !;↵
    0.07
    ()?;↵
    0.07
    .";
↵
    0.07
    __);↵↵
    0.07
    (attributes
    0.07
    äß
    0.07
    <?↵
    0.07
    Act Density 0.001%

    No Known Activations