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

    Neuronpedia

    INDEX
    Explanations

    javascript function callbacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istet
    0.45
    Dann
    0.42
     ہوسک
    0.41
     требований
    0.40
    Эти
    0.40
    玽
    0.40
    %";
    0.39
    粔
    0.39
    এটি
    0.39
    nless
    0.39
    POSITIVE LOGITS
     function
    1.23
    (()
    1.16
     ()=>{
    1.13
     ()
    1.12
    function
    1.09
    ()=>{
    1.09
     ()=>
    1.06
    ={()
    1.04
    (()=>{
    0.98
     (()
    0.96
    Act Density 0.016%

    No Known Activations