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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     introduction
    -0.07
     gu
    -0.06
     malloc
    -0.06
     pers
    -0.06
    pur
    -0.06
     �
    -0.06
     lượng
    -0.06
    _init
    -0.06
     prés
    -0.06
    세
    -0.06
    POSITIVE LOGITS
     。↵
    0.08
    _registered
    0.07
     　 　 　 　 　 　 　 　
    0.07
     (_.
    0.06
     Pest
    0.06
     filmmaker
    0.06
    !");↵
    0.06
     зелен
    0.06
     candidate
    0.06
    饮
    0.06
    Act Density 0.001%

    No Known Activations