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

    Neuronpedia

    INDEX
    Explanations

    percentage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овари
    -0.07
     thoughtful
    -0.07
    处
    -0.06
    parallel
    -0.06
    々
    -0.06
     hyper
    -0.06
    ames
    -0.06
    operators
    -0.06
    首
    -0.06
     farming
    -0.06
    POSITIVE LOGITS
    ंद
    0.07
    ][
    0.06
     zoning
    0.06
    /se
    0.06
    .addNode
    0.06
     addiction
    0.06
    .IntegerField
    0.06
    >");↵↵
    0.06
    emo
    0.06
    }<
    0.06
    Act Density 0.037%

    No Known Activations