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

    Neuronpedia

    INDEX
    Explanations

    lifetime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .accuracy
    -0.07
     rendering
    -0.07
     Wor
    -0.06
    appropriate
    -0.06
    /py
    -0.06
    174
    -0.06
     congestion
    -0.06
     invented
    -0.06
     obvykle
    -0.06
     mou
    -0.06
    POSITIVE LOGITS
     lifelong
    0.08
     松
    0.07
    (trim
    0.07
    lotte
    0.06
    闪
    0.06
     stál
    0.06
    월
    0.06
    >/',
    0.06
     gameTime
    0.06
    Opens
    0.06
    Act Density 0.007%

    No Known Activations