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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.06
     estekak
    -0.97
     ſeveral
    -0.95
     Efq
    -0.90
     ſche
    -0.90
     Diſ
    -0.89
     myſelf
    -0.89
     Majefty
    -0.88
     Houſe
    -0.88
     iſt
    -0.86
    POSITIVE LOGITS
      
    0.49
     it
    0.48
    ↵
    0.45
     his
    0.45
     Bar
    0.45
     a
    0.43
     
    0.43
     du
    0.40
    {(-
    0.39
     i
    0.39
    Act Density 0.044%

    No Known Activations