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

    Neuronpedia

    INDEX
    Explanations

    numerical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Semantic
    -0.07
    诜
    -0.07
     tö
    -0.07
     çerç
    -0.07
    <Token
    -0.07
    编制
    -0.07
    .Ed
    -0.07
    בוחר
    -0.07
    住宿
    -0.07
     FRE
    -0.06
    POSITIVE LOGITS
    bbe
    0.07
    AFP
    0.07
     loss
    0.07
    מסר
    0.07
     unknown
    0.07
     noi
    0.06
     have
    0.06
    //↵↵↵
    0.06
     stole
    0.06
    !!)↵
    0.06
    Act Density 0.376%

    No Known Activations