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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     /*!↵
    -0.07
    ่อไป
    -0.06
    :`~
    -0.06
     FA
    -0.06
    ']*
    -0.06
    -0.06
    JECTION
    -0.06
    -0.06
    -house
    -0.06
    ("'"
    -0.06
    POSITIVE LOGITS
    十八
    0.07
     ofrece
    0.07
     servicios
    0.07
     Pornhub
    0.07
     brisk
    0.06
    631
    0.06
    express
    0.06
    .number
    0.06
     Clarence
    0.06
    /how
    0.06
    Act Density 0.000%

    No Known Activations