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

    Neuronpedia

    INDEX
    Explanations

    science/medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Man
    -0.77
     Ma
    -0.74
     ‘
    -0.69
     '
    -0.68
     
    -0.65
     No
    -0.64
     (
    -0.64
     "
    -0.64
     O
    -0.63
     “
    -0.63
    POSITIVE LOGITS
     myſelf
    1.38
     itſelf
    1.34
     purpoſe
    1.34
     Efq
    1.33
     Monfieur
    1.32
     Diſ
    1.31
     Jefus
    1.30
     raiſ
    1.28
     Reſ
    1.28
     pleaſure
    1.27
    Act Density 0.214%

    No Known Activations