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

    Neuronpedia

    INDEX
    Explanations

    Submitted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.96
     betweenstory
    -0.95
     myſelf
    -0.95
    ſelves
    -0.93
     pleaſure
    -0.88
    ſelf
    -0.88
     محفوظة
    -0.88
     ſever
    -0.86
     greateſt
    -0.85
     GenerationType
    -0.84
    POSITIVE LOGITS
     of
    0.65
     O
    0.61
     Z
    0.59
     c
    0.57
     o
    0.54
     for
    0.54
     M
    0.52
     n
    0.51
     C
    0.50
     N
    0.50
    Act Density 1.655%

    No Known Activations