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
    위원
    -0.07
     bols
    -0.07
    онд
    -0.07
     accusations
    -0.06
    chw
    -0.06
     클래스
    -0.06
     vanish
    -0.06
    ナ
    -0.06
     photons
    -0.06
    ǎ
    -0.06
    POSITIVE LOGITS
     repell
    0.07
     #__
    0.07
     قاب
    0.07
    (operator
    0.07
     precip
    0.07
    .SaveChanges
    0.06
     CET
    0.06
     &___
    0.06
     되는
    0.06
     {|
    0.06
    Act Density 0.002%

    No Known Activations