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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     które
    -0.07
    𝘌
    -0.07
    钥匙
    -0.07
    琏
    -0.07
     каталог
    -0.07
    졔
    -0.07
     indirect
    -0.06
    جال
    -0.06
     hứng
    -0.06
     mange
    -0.06
    POSITIVE LOGITS
     #[
    0.08
    ='';↵
    0.07
    _pv
    0.07
    '],$
    0.06
    =>$
    0.06
    我校
    0.06
    תופעה
    0.06
    '],
↵
    0.06
    "){
↵
    0.06
    ";
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations