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

    Neuronpedia

    INDEX
    Explanations

    trio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -2.30
     myſelf
    -2.06
     Theſe
    -1.96
     Majefty
    -1.94
     itſelf
    -1.94
     Monfieur
    -1.92
     photolibrary
    -1.90
     ―――――
    -1.88
     Jefus
    -1.80
     ་་
    -1.78
    POSITIVE LOGITS
     
    1.30
     in
    1.11
     (
    1.09
    ,
    1.06
     for
    1.02
     and
    0.99
    ↵↵
    0.95
     the
    0.94
     "
    0.94
     a
    0.94
    Act Density 0.141%

    No Known Activations