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

    Neuronpedia

    INDEX
    Explanations

    All

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     میلادی
    -0.07
    warning
    -0.07
     standards
    -0.07
     prepared
    -0.07
    操作
    -0.07
     malicious
    -0.07
    StateManager
    -0.07
    ackson
    -0.06
    инок
    -0.06
     tsunami
    -0.06
    POSITIVE LOGITS
     دریا
    0.06
     noisy
    0.06
     =>
↵
    0.06
     Rhe
    0.06
     miss
    0.06
     svaz
    0.06
     wiping
    0.06
    rosse
    0.06
    挂
    0.06
     ipairs
    0.06
    Act Density 0.002%

    No Known Activations