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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wang
    -0.07
     Lag
    -0.06
    봉
    -0.06
     directory
    -0.06
    Pane
    -0.06
    愉悦
    -0.06
    рин
    -0.06
    換
    -0.06
     BTC
    -0.06
    行李
    -0.06
    POSITIVE LOGITS
    もなく
    0.07
    /mod
    0.07
    =}
    0.07
    劄
    0.07
     Past
    0.07
    老
    0.07
    -kit
    0.06
    _TIMES
    0.06
     alter
    0.06
     govern
    0.06
    Act Density 0.387%

    No Known Activations