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

    Neuronpedia

    INDEX
    Explanations

    Sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    r
    -0.66
    s
    -0.63
     Bar
    -0.58
     
    -0.56
     in
    -0.56
     (
    -0.54
     get
    -0.53
    n
    -0.52
     R
    -0.50
     a
    -0.49
    POSITIVE LOGITS
     Reſ
    1.09
     itſelf
    1.03
     myſelf
    1.01
     Jefus
    0.96
     Efq
    0.95
     Chriftian
    0.94
     Diſ
    0.94
     ftate
    0.91
     Anſ
    0.91
     ſtate
    0.91
    Act Density 0.375%

    No Known Activations