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

    Neuronpedia

    INDEX
    Explanations

    Code with brackets and 1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etre
    -0.07
    oystick
    -0.07
    创客
    -0.07
    席执行官
    -0.07
    Į
    -0.07
    ichtet
    -0.06
     đạt
    -0.06
    萧
    -0.06
    ixels
    -0.06
    kov
    -0.06
    POSITIVE LOGITS
    评议
    0.07
    .offer
    0.07
    屙
    0.07
    绨
    0.06
    .backward
    0.06
     onwards
    0.06
     Zone
    0.06
     City
    0.06
     carbonate
    0.06
     ├──
    0.06
    Act Density 0.008%

    No Known Activations