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

    Neuronpedia

    INDEX
    Explanations

    SMS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝙥
    -0.08
    =start
    -0.08
     natuur
    -0.07
    蘑
    -0.07
    跶
    -0.07
    logg
    -0.07
    🇶
    -0.07
     numOf
    -0.07
    艺
    -0.07
    众人
    -0.06
    POSITIVE LOGITS
    短信
    0.08
    ',
↵
    0.08
     worrying
    0.07
    /sdk
    0.07
    App
    0.07
    ",
↵
    0.07
    ),
↵
    0.07
    赌场
    0.07
    Javascript
    0.07
     guessed
    0.07
    Act Density 0.002%

    No Known Activations