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

    Neuronpedia

    INDEX
    Explanations

    erotic descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explaining
    -0.07
    (debug
    -0.07
    ducer
    -0.07
    坚定
    -0.06
     even
    -0.06
     bütün
    -0.06
    .steps
    -0.06
    親
    -0.06
    ientes
    -0.06
     swollen
    -0.06
    POSITIVE LOGITS
     territory
    0.07
     Recently
    0.07
    CrLf
    0.07
    苌
    0.07
     RIGHTS
    0.07
     Baxter
    0.07
    .year
    0.06
    怀里
    0.06
    Љ
    0.06
    "crypto
    0.06
    Act Density 0.024%

    No Known Activations