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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Susan
    -0.07
    orgen
    -0.07
    enary
    -0.07
    hammad
    -0.07
    isting
    -0.07
     matter
    -0.07
    غض
    -0.07
     Anthony
    -0.07
     that
    -0.07
    减弱
    -0.06
    POSITIVE LOGITS
    的家庭
    0.07
    诂
    0.07
     المناسب
    0.07
    該
    0.07
    惆
    0.07
     פר
    0.07
    뤘
    0.07
    字符
    0.07
    ]interface
    0.07
    >(_
    0.07
    Act Density 0.080%

    No Known Activations