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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﾚ
    -0.07
    ROUND
    -0.07
     wav
    -0.07
    _end
    -0.07
    chief
    -0.07
    එ
    -0.07
     CARE
    -0.07
    anceled
    -0.07
     =>$
    -0.07
     Funding
    -0.07
    POSITIVE LOGITS
     agreement
    0.08
    无障碍
    0.07
    (surface
    0.06
     authenticated
    0.06
    莫斯
    0.06
    ;
↵
↵
↵
↵
    0.06
     ogó
    0.06
    UDO
    0.06
    opcion
    0.06
    迷惑
    0.06
    Act Density 0.002%

    No Known Activations