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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wholes
    -0.08
    2
    -0.08
    Vers
    -0.07
    ,
    -0.07
     goes
    -0.07
    <Order
    -0.07
    Following
    -0.07
    $",
    -0.07
     verb
    -0.07
    主题活动
    -0.06
    POSITIVE LOGITS
    ᗭ
    0.08
     the
    0.07
    0.07
    张某
    0.07
     and
    0.07
     PERFORMANCE
    0.07
     P
    0.07
     RMS
    0.06
    .RequestParam
    0.06
    IST
    0.06
    Act Density 1.719%

    No Known Activations