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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    son
    -0.07
     ensure
    -0.07
     latest
    -0.07
    Not
    -0.07
     cent
    -0.07
     indirectly
    -0.07
    آخر
    -0.07
    .is
    -0.07
    .Http
    -0.07
     absolutely
    -0.06
    POSITIVE LOGITS
     fry
    0.07
     TJ
    0.07
    目前已
    0.07
     untranslated
    0.07
     endforeach
    0.07
    ▫
    0.07
    🥳
    0.07
    ..<
    0.07
     artificially
    0.06
    nj
    0.06
    Act Density 0.045%

    No Known Activations