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

    Neuronpedia

    INDEX
    Explanations

    Legal codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caucus
    -0.08
     renowned
    -0.07
    差异化
    -0.07
     sensations
    -0.07
    Fs
    -0.07
    .Email
    -0.07
     retract
    -0.06
    研发
    -0.06
     manifest
    -0.06
     welcoming
    -0.06
    POSITIVE LOGITS
    끌
    0.07
    irical
    0.07
    .createTextNode
    0.07
     beğ
    0.07
    就把
    0.06
    ܒ
    0.06
    (utf
    0.06
     Hera
    0.06
     $#
    0.06
    מב
    0.06
    Act Density 0.006%

    No Known Activations