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

    Neuronpedia

    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HelloWorld
    -0.07
    _you
    -0.07
    ตลอด
    -0.06
     cậu
    -0.06
     băng
    -0.06
     dots
    -0.06
    .jsdelivr
    -0.06
     colleague
    -0.06
     domin
    -0.06
    .isNotBlank
    -0.06
    POSITIVE LOGITS
    σταση
    0.07
    (levels
    0.07
    yonel
    0.06
     intrinsic
    0.06
    uddy
    0.06
    ρκ
    0.06
    ackbar
    0.06
     엄마
    0.06
    quer
    0.06
    비스
    0.06
    Act Density 0.319%

    No Known Activations