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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bun
    -0.07
    atica
    -0.06
    روت
    -0.06
     NSK
    -0.06
    陆
    -0.06
     національ
    -0.06
    _Sh
    -0.06
    antu
    -0.06
     Garten
    -0.06
    iseconds
    -0.06
    POSITIVE LOGITS
    QUE
    0.08
    entin
    0.07
    chner
    0.06
     nud
    0.06
    ITHUB
    0.06
     conqu
    0.06
    225
    0.06
     romance
    0.06
    !***
    0.06
     epoll
    0.06
    Act Density 0.000%

    No Known Activations