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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ―――――
    -0.89
     photolibrary
    -0.80
    WSGI
    -0.80
     itſelf
    -0.78
     Forumite
    -0.77
     ་་
    -0.76
     themſelves
    -0.75
     endregion
    -0.75
    WriteBarrier
    -0.75
     myſelf
    -0.75
    POSITIVE LOGITS
     I
    0.63
    .
    0.58
    ↵↵
    0.57
     and
    0.56
    ,
    0.55
     (
    0.54
    in
    0.54
     t
    0.54
    …
    0.54
     to
    0.53
    Act Density 1.547%

    No Known Activations