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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BUCKET
    -0.07
    onents
    -0.07
    ована
    -0.07
     �
    -0.06
     vítěz
    -0.06
     مرحله
    -0.06
    Hover
    -0.06
    			
↵			
↵
    -0.06
     Estados
    -0.06
    (Game
    -0.06
    POSITIVE LOGITS
    Sentence
    0.06
     ('\
    0.06
     Percent
    0.06
     знаю
    0.06
     поч
    0.06
    _same
    0.06
    mj
    0.06
    (Api
    0.06
    length
    0.06
    says
    0.06
    Act Density 0.185%

    No Known Activations