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

    Neuronpedia

    INDEX
    Explanations

    here's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sqlalchemy
    0.35
     Tenemos
    0.35
     لقد
    0.33
    ا۔
    0.33
    Isopropyl
    0.33
    Gin
    0.31
     يكن
    0.31
     얼
    0.31
     المثال
    0.31
    سلام
    0.31
    POSITIVE LOGITS
     here
    0.70
     are
    0.64
     здесь
    0.52
     aquí
    0.50
    here
    0.49
    Here
    0.48
     aqui
    0.47
     jsou
    0.47
     Here
    0.46
     HERE
    0.45
    Act Density 0.150%

    No Known Activations