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

    Neuronpedia

    INDEX
    Explanations

    resetting index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    guas
    0.45
     impresionante
    0.45
     legenda
    0.42
     depresión
    0.42
     भट्ट
    0.41
    elesaian
    0.41
     Tenemos
    0.41
    használ
    0.41
    درسة
    0.41
     موفق
    0.41
    POSITIVE LOGITS
    Instance
    0.51
    _
    0.49
    ());
    0.46
     theirs
    0.46
     begin
    0.45
    ()
    0.45
    (),
    0.45
    (){
    0.45
     ints
    0.45
    并
    0.45
    Act Density 0.003%

    No Known Activations