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

    Neuronpedia

    INDEX
    Explanations

    Cell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ประธาน
    -0.07
    눉
    -0.07
    酦
    -0.07
    你們
    -0.06
    .join
    -0.06
    \Active
    -0.06
     Bunifu
    -0.06
    $errors
    -0.06
    换取
    -0.06
    /ubuntu
    -0.06
    POSITIVE LOGITS
     Armor
    0.07
     Coron
    0.07
     órgão
    0.07
     spin
    0.07
    Courses
    0.07
    开关
    0.07
     Cuisine
    0.07
    债券
    0.07
    sold
    0.07
    Corn
    0.06
    Act Density 0.001%

    No Known Activations