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

    Neuronpedia

    INDEX
    Explanations

    sort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ſeveral
    -1.02
     Efq
    -1.01
     sort
    -0.99
     assortment
    -0.98
     itſelf
    -0.98
     variety
    -0.96
     pleaſure
    -0.96
     myſelf
    -0.95
    RenderAtEndOf
    -0.93
     themſelves
    -0.93
    POSITIVE LOGITS
     of
    0.78
     to
    0.75
    s
    0.48
    ly
    0.46
    to
    0.45
    .
    0.43
     but
    0.41
     than
    0.38
    ็ม
    0.38
    ments
    0.37
    Act Density 0.070%

    No Known Activations