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

    Neuronpedia

    INDEX
    Explanations

    nature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ${
    -0.07
     convictions
    -0.06
    -0.06
    以来
    -0.06
    =[];↵
    -0.06
    维
    -0.06
    減
    -0.06
    -0.06
    -0.06
    -0.06
    POSITIVE LOGITS
     nature
    0.08
     both
    0.07
    Wow
    0.07
     natural
    0.06
     Took
    0.06
    natural
    0.06
     Natural
    0.06
     NOM
    0.06
    сор
    0.06
     deceased
    0.06
    Act Density 0.012%

    No Known Activations