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

    Neuronpedia

    INDEX
    Explanations

    opinions and self-identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruins
    -0.07
    \Console
    -0.07
     Yang
    -0.07
    ////////////////////////////////////////////////////////////////
    -0.07
     insurgents
    -0.07
    ALTER
    -0.07
     STATIC
    -0.06
     Copyright
    -0.06
    Screenshot
    -0.06
     Simpl
    -0.06
    POSITIVE LOGITS
    [j
    0.07
    (segment
    0.06
     」
    0.06
    (country
    0.06
     спроб
    0.06
    “,
    0.06
    ７
    0.06
    (xs
    0.06
    ensive
    0.06
     vem
    0.06
    Act Density 0.016%

    No Known Activations