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

    Neuronpedia

    INDEX
    Explanations

    technical vocabulary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ſelf
    -1.23
     Majefty
    -1.15
     Diſ
    -1.12
     Efq
    -1.11
     Reſ
    -1.09
     ſta
    -1.07
     purpoſe
    -1.06
    ſelves
    -1.05
     Jefus
    -1.05
     Monfieur
    -1.05
    POSITIVE LOGITS
     cu
    0.62
     mo
    0.55
     to
    0.51
    i
    0.50
     ne
    0.49
     lo
    0.48
     uno
    0.47
     la
    0.45
     bis
    0.45
     ch
    0.44
    Act Density 0.089%

    No Known Activations