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

    Neuronpedia

    INDEX
    Explanations

    mk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    y
    -0.97
    t
    -0.92
    c
    -0.91
    d
    -0.90
    m
    -0.88
    l
    -0.87
    n
    -0.84
    ly
    -0.83
    mk
    -0.81
    s
    -0.81
    POSITIVE LOGITS
     itſelf
    1.30
     myſelf
    1.27
     Efq
    1.23
     themſelves
    1.14
     purpoſe
    1.13
     Jefus
    1.12
     himſelf
    1.06
     raiſ
    1.06
     houſe
    1.04
     greateſt
    1.04
    Act Density 0.149%

    No Known Activations