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

    Neuronpedia

    INDEX
    Explanations

    torch.Tensor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rost
    0.98
     Smith
    0.93
     granny
    0.90
     Tina
    0.89
     Kimmel
    0.87
     Holl
    0.86
     Garcia
    0.86
     SMITH
    0.84
     Granny
    0.84
     girls
    0.83
    POSITIVE LOGITS
    puzzle
    0.85
    Š
    0.81
     κε
    0.80
     Monza
    0.79
    <0xAB>
    0.79
    Puzzle
    0.78
     Matsuda
    0.77
     മൊ
    0.76
     Araújo
    0.75
     Sorrent
    0.75
    Act Density 0.785%

    No Known Activations