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

    Neuronpedia

    INDEX
    Explanations

    function followed by parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    スカート
    0.46
    許可
    0.43
     elegans
    0.42
    ellington
    0.39
     fissures
    0.39
     সংখ
    0.39
    middels
    0.39
    相
    0.39
     ந
    0.39
    دة
    0.39
    POSITIVE LOGITS
    ↵
    0.45
     kife
    0.43
     {
    0.42
     ActionListener
    0.38
    itali
    0.38
     {});
    0.37
    ."},
    0.37
     inside
    0.36
     xyz
    0.36
    (){
    0.36
    Act Density 0.010%

    No Known Activations