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

    Neuronpedia

    INDEX
    Explanations

    washing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    希望
    0.54
    0.52
     Islam
    0.52
     EU
    0.50
    ́c
    0.50
    4
    0.49
     జరుగు
    0.47
    妏
    0.47
     ug
    0.47
    指定
    0.46
    POSITIVE LOGITS
    🎑
    0.61
     perplex
    0.59
     యొక్క
    0.59
    openia
    0.58
     While
    0.57
     செய்தனர்
    0.57
     shayari
    0.56
     மற்றும்
    0.56
     इसको
    0.56
     Thickness
    0.56
    Act Density 0.001%

    No Known Activations