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

    Neuronpedia

    INDEX
    Explanations

    RAM size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     routes
    -0.08
    ่อง
    -0.07
    ОН
    -0.07
    虸
    -0.06
    oi
    -0.06
    없
    -0.06
     china
    -0.06
     sak
    -0.06
    YM
    -0.06
    🏤
    -0.06
    POSITIVE LOGITS
    passwd
    0.08
    zer
    0.07
    ถอน
    0.07
    yx
    0.07
     mods
    0.07
    *X
    0.07
     Absolute
    0.07
    opacity
    0.07
    Dog
    0.07
     Throwable
    0.07
    Act Density 0.016%

    No Known Activations