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

    Neuronpedia

    INDEX
    Explanations

    negative states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liebe
    -0.07
    .mi
    -0.06
     непосред
    -0.06
     geen
    -0.06
     ej
    -0.06
     Procedure
    -0.06
    .Manager
    -0.06
     Irvine
    -0.06
     clk
    -0.06
     eliminated
    -0.06
    POSITIVE LOGITS
    ERT
    0.07
     빠
    0.06
     Tây
    0.06
    .slf
    0.06
     trở
    0.06
    聲
    0.06
    REN
    0.06
    _AXIS
    0.06
    ті
    0.06
    llll
    0.06
    Act Density 0.109%

    No Known Activations