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

    Neuronpedia

    INDEX
    Explanations

    university names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     b
    0.93
    ADELPHIA
    0.88
     bulletins
    0.87
     clue
    0.86
     excerpts
    0.85
     androidx
    0.84
     clues
    0.83
    MediaStore
    0.82
     obfusc
    0.81
     Архивная
    0.81
    POSITIVE LOGITS
     इसमें
    1.11
    Computational
    1.03
     đạp
    1.02
     વખત
    1.02
     Computational
    1.02
     Интер
    0.98
    Terror
    0.98
     वहां
    0.97
     Imágenes
    0.96
    Тре
    0.95
    Act Density 0.000%

    No Known Activations