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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ż
    -0.07
     법
    -0.07
     tik
    -0.07
    头
    -0.07
    usk
    -0.07
    铠
    -0.07
     שיהיה
    -0.07
    𝙺
    -0.07
    Nuitka
    -0.07
     college
    -0.07
    POSITIVE LOGITS
     adjustable
    0.07
    Invite
    0.07
    lime
    0.07
    );
↵
↵
↵
    0.07
    )|
    0.07
    (Room
    0.07
    捨て
    0.07
     bekom
    0.07
    _descr
    0.06
     bert
    0.06
    Act Density 0.120%

    No Known Activations