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

    Neuronpedia

    INDEX
    Explanations

    Colon or quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CAT
    -0.07
    جمة
    -0.07
    charset
    -0.06
    ，更
    -0.06
    _SECRET
    -0.06
    erg
    -0.06
    PUR
    -0.06
    resp
    -0.06
    éric
    -0.06
    έρει
    -0.06
    POSITIVE LOGITS
     _↵
    0.08
     대상
    0.07
      
↵
    0.07
    ',
↵
    0.07
    ']:↵
    0.07
     (){↵
    0.07
    ()")↵
    0.07
    )).↵
    0.06
    ै.↵
    0.06
     ".↵
    0.06
    Act Density 0.045%

    No Known Activations