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

    Neuronpedia

    INDEX
    Explanations

    performance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wel
    -0.07
     Mix
    -0.06
    芋
    -0.06
    otp
    -0.06
    �
    -0.06
    };↵↵
    -0.06
    算
    -0.06
     jugar
    -0.06
    辟
    -0.06
    蚨
    -0.06
    POSITIVE LOGITS
     performance
    0.10
     Performance
    0.09
    ГО
    0.08
    0.08
     the
    0.07
    -Year
    0.07
    性能
    0.07
    增速
    0.07
     더욱
    0.07
     Operations
    0.07
    Act Density 0.039%

    No Known Activations