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

    Neuronpedia

    INDEX
    Explanations

    tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chopping
    -0.07
     adip
    -0.07
     równ
    -0.07
     vých
    -0.06
     Coc
    -0.06
     depot
    -0.06
     Вы
    -0.06
    픽
    -0.06
     بأ
    -0.06
    responses
    -0.06
    POSITIVE LOGITS
     pathlib
    0.07
    ListNode
    0.07
     Adding
    0.07
     Pipeline
    0.07
    ToArray
    0.07
    ()}</
    0.06
    Crud
    0.06
     Families
    0.06
    .Formatting
    0.06
     bug
    0.06
    Act Density 0.000%

    No Known Activations