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

    Neuronpedia

    INDEX
    Explanations

    structured text/problem breakdown

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dex
    -0.07
     ná
    -0.07
     Gemini
    -0.07
     méně
    -0.06
    ++.
    -0.06
     �
    -0.06
    овані
    -0.06
     příjem
    -0.06
     віднос
    -0.06
     thẩm
    -0.06
    POSITIVE LOGITS
    nh
    0.07
    /Input
    0.07
     unix
    0.07
     like
    0.07
    "B
    0.06
    assed
    0.06
     {-
    0.06
     coupons
    0.06
     endings
    0.06
    \<
    0.06
    Act Density 0.003%

    No Known Activations