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

    Neuronpedia

    INDEX
    Explanations

    code properties and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.40
     बजा
    0.39
     ರೀತಿ
    0.39
    Closed
    0.39
    Gener
    0.38
    列
    0.38
    转载
    0.38
     generics
    0.37
    Closing
    0.37
    қ
    0.36
    POSITIVE LOGITS
     {
    0.57
    (){
    0.42
    ?
    0.41
    ]{
    0.38
     (){
    0.38
    ocation
    0.37
     দেব
    0.37
    urchase
    0.36
    orado
    0.36
     =>
    0.36
    Act Density 0.010%

    No Known Activations