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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енного
    -0.08
    \Message
    -0.07
     zda
    -0.06
     modest
    -0.06
    았다
    -0.06
    ارت
    -0.06
     pragmatic
    -0.06
    	Array
    -0.06
    lama
    -0.06
     мит
    -0.06
    POSITIVE LOGITS
    _DEF
    0.07
     seul
    0.06
    -commit
    0.06
    -ab
    0.06
     disposing
    0.06
     rd
    0.06
    -sp
    0.06
    μιουργ
    0.06
    recur
    0.06
    -seat
    0.06
    Act Density 0.003%

    No Known Activations