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

    Neuronpedia

    INDEX
    Explanations

    location and organization names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     da
    -0.73
     ser
    -0.66
     ~
    -0.59
     de
    -0.58
     no
    -0.57
    IRUS
    -0.56
     por
    -0.55
     van
    -0.55
     the
    -0.55
     f
    -0.54
    POSITIVE LOGITS
     purpoſe
    1.37
     Efq
    1.34
     Jefus
    1.34
     itſelf
    1.30
     pleaſure
    1.30
     Diſ
    1.30
     Monfieur
    1.30
     myſelf
    1.29
     Reſ
    1.25
     whoſe
    1.23
    Act Density 0.134%

    No Known Activations