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

    Neuronpedia

    INDEX
    Explanations

    Taking over a project

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีล
    -0.07
     birik
    -0.07
     Мик
    -0.06
    中华
    -0.06
     рассчит
    -0.06
     skeptical
    -0.06
    Fake
    -0.06
     unf
    -0.06
    .Board
    -0.06
    话
    -0.06
    POSITIVE LOGITS
    gon
    0.06
     userId
    0.06
    werp
    0.06
    continued
    0.06
     pkg
    0.06
     assumptions
    0.06
    مح
    0.06
    溪
    0.06
     Hans
    0.06
     RELEASE
    0.06
    Act Density 0.003%

    No Known Activations