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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .n
    -0.07
    .ne
    -0.07
     فن
    -0.06
    inar
    -0.06
     ia
    -0.06
    /API
    -0.06
    agar
    -0.06
    career
    -0.06
     WHO
    -0.06
    .on
    -0.06
    POSITIVE LOGITS
    ूब
    0.07
    .charAt
    0.06
     undisclosed
    0.06
    .charCodeAt
    0.06
    $↵↵
    0.06
    (BuildContext
    0.06
     comfortable
    0.06
     nonetheless
    0.06
    ิงหาคม
    0.06
     دلار
    0.06
    Act Density 0.155%

    No Known Activations