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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    农业
    -0.08
    AS
    -0.07
     Athena
    -0.07
    协商
    -0.07
    宸
    -0.07
     чуть
    -0.07
    统筹
    -0.07
     소개
    -0.07
    倒
    -0.06
     Andy
    -0.06
    POSITIVE LOGITS
    >';
↵
    0.09
    ]",↵
    0.08
    .getOrElse
    0.08
    _overlap
    0.07
    endcode
    0.07
    }];↵
    0.07
    涞
    0.07
    `}↵
    0.07
     Appears
    0.07
    restriction
    0.07
    Act Density 0.005%

    No Known Activations