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

    Neuronpedia

    INDEX
    Explanations

    Car accidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    watch
    -0.06
     лекар
    -0.06
     Cent
    -0.06
     Recipe
    -0.06
    placer
    -0.06
    Watch
    -0.06
     flere
    -0.06
     banyak
    -0.06
     pan
    -0.06
    ism
    -0.06
    POSITIVE LOGITS
    认
    0.07
     dividing
    0.07
    ught
    0.07
    農
    0.06
     overposting
    0.06
    _REMOTE
    0.06
    寝
    0.06
    ((*
    0.06
     जनत
    0.06
    讲
    0.06
    Act Density 0.038%

    No Known Activations