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

    Neuronpedia

    INDEX
    Explanations

    python code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complained
    0.90
    <0xB7>
    0.90
     Kaj
    0.88
     Kendra
    0.83
     Grav
    0.81
     Saj
    0.80
     Kavan
    0.80
     Banj
    0.79
    pé
    0.78
     Cus
    0.77
    POSITIVE LOGITS
     __
    1.34
    __
    1.09
    (__
    0.98
     ___
    0.92
     _
    0.88
     Arti
    0.86
    ,__
    0.86
     "__
    0.83
     "_
    0.83
     [_
    0.80
    Act Density 0.176%

    No Known Activations