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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    快速
    -0.07
     trải
    -0.07
     placed
    -0.07
     Powell
    -0.06
     Serif
    -0.06
     всі
    -0.06
     سرعت
    -0.06
     імен
    -0.06
     busy
    -0.06
    通常
    -0.06
    POSITIVE LOGITS
     incon
    0.08
     غیر
    0.08
     ind
    0.08
     inde
    0.07
     irres
    0.07
     нев
    0.07
     diminished
    0.07
     uncomp
    0.07
     A
    0.07
     م
    0.07
    Act Density 0.044%

    No Known Activations