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

    Neuronpedia

    INDEX
    Explanations

    sequence/adjacency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.55
     myſelf
    -1.54
    NUMX
    -1.51
     $_"
    -1.40
     himſelf
    -1.38
    DockStyle
    -1.37
     themſelves
    -1.36
     مشين
    -1.34
     Forumite
    -1.34
     ſtate
    -1.34
    POSITIVE LOGITS
    ,
    0.94
     is
    0.93
     and
    0.89
     to
    0.87
    .
    0.87
     (
    0.82
     or
    0.82
     
    0.81
     in
    0.78
    /
    0.74
    Act Density 0.038%

    No Known Activations