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

    Neuronpedia

    INDEX
    Explanations

    add makes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     add
    -1.22
     Paul
    -0.92
     adds
    -0.86
     makes
    -0.81
    Paul
    -0.81
    add
    -0.79
     added
    -0.79
     pair
    -0.75
    ,
    -0.74
     (
    -0.73
    POSITIVE LOGITS
     Efq
    1.30
     Jefus
    1.24
     purpoſe
    1.23
     Reſ
    1.18
     Houſe
    1.17
     Diſ
    1.16
     itſelf
    1.14
     pleaſure
    1.14
    ſelf
    1.13
     Chriftian
    1.13
    Act Density 1.906%

    No Known Activations