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

    Neuronpedia

    INDEX
    Explanations

    assigned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dom
    -0.07
    累了
    -0.06
     Longer
    -0.06
    _male
    -0.06
    fried
    -0.06
     nur
    -0.06
     cues
    -0.06
     Vide
    -0.06
     glean
    -0.06
    "Do
    -0.06
    POSITIVE LOGITS
     الاجتماعي
    0.08
    =b
    0.07
    웃
    0.07
    こんにちは
    0.07
    chrono
    0.07
    )↵↵↵↵↵↵↵↵
    0.07
    ']}
    0.07
    뜽
    0.07
    Microsoft
    0.07
    .messaging
    0.07
    Act Density 0.008%

    No Known Activations