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

    Neuronpedia

    INDEX
    Explanations

    say "would"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StreamWriter
    -0.07
     Stars
    -0.07
     Leak
    -0.06
    Century
    -0.06
     elementType
    -0.06
    NORMAL
    -0.06
    }">↵
    -0.06
     pagina
    -0.06
     Trevor
    -0.06
     Spaces
    -0.05
    POSITIVE LOGITS
     gar
    0.07
     مشاه
    0.06
    МО
    0.06
     experiment
    0.06
    디
    0.06
    ,V
    0.06
     irm
    0.06
     než
    0.06
     stringBuffer
    0.06
    「あ
    0.06
    Act Density 0.029%

    No Known Activations