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

    Neuronpedia

    INDEX
    Explanations

    sw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     х
    -0.07
     REC
    -0.07
     ø
    -0.06
    .Our
    -0.06
    )i
    -0.06
     чор
    -0.06
     fuer
    -0.06
     Imp
    -0.06
     chairs
    -0.06
     Red
    -0.06
    POSITIVE LOGITS
     درون
    0.07
    <Application
    0.07
     probing
    0.07
    ******
↵
    0.07
     اینکه
    0.07
    whole
    0.06
    greSQL
    0.06
    laví
    0.06
    "]],↵
    0.06
    [q
    0.06
    Act Density 0.000%

    No Known Activations