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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -minute
    -0.30
    ç²¾
    -0.26
    romatic
    -0.26
    orsk
    -0.26
    hort
    -0.25
    à§İ
    -0.25
    ÑĭÑĤа
    -0.25
    minute
    -0.25
     kami
    -0.23
     пÑĢог
    -0.23
    POSITIVE LOGITS
     Ca
    0.25
    hap
    0.25
    åħ¨å¤©
    0.24
    代è¨Ģ
    0.24
    Own
    0.24
    éļ¼
    0.24
     confer
    0.24
    ä¸ĵå±ŀ
    0.24
    代è¨Ģ人
    0.24
    umba
    0.23
    Act Density 0.010%

    No Known Activations