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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pedido
    -0.08
     ابت
    -0.07
     теч
    -0.07
     بگ
    -0.07
    Precio
    -0.07
    녀
    -0.06
     pově
    -0.06
     comfort
    -0.06
    .helper
    -0.06
    .RightToLeft
    -0.06
    POSITIVE LOGITS
    rene
    0.07
    Cx
    0.06
    spy
    0.06
    .python
    0.06
     MPEG
    0.06
     мот
    0.06
     hd
    0.06
     fi
    0.06
    蘇
    0.06
    erman
    0.06
    Act Density 0.003%

    No Known Activations