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

    Neuronpedia

    INDEX
    Explanations

    /**

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diplomats
    -0.07
     queda
    -0.07
    ША
    -0.06
     slide
    -0.06
    ฟร
    -0.06
     обы
    -0.06
     dragons
    -0.06
     commanded
    -0.06
    ))[
    -0.06
     Su
    -0.06
    POSITIVE LOGITS
    (description
    0.07
    Years
    0.07
    weet
    0.07
     verbally
    0.06
    (mask
    0.06
     \<^
    0.06
    >>();↵↵
    0.06
    _disp
    0.06
     defaults
    0.06
     annual
    0.06
    Act Density 0.016%

    No Known Activations