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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (nc
    -0.08
    February
    -0.07
     dow
    -0.06
    Tyler
    -0.06
     Nash
    -0.06
     Circular
    -0.06
    從
    -0.06
    337
    -0.06
    (dataset
    -0.06
    loaded
    -0.06
    POSITIVE LOGITS
    :::/
    0.06
     mkdir
    0.06
    ointment
    0.06
     onSuccess
    0.06
     เมตร
    0.06
     خیلی
    0.06
     매매
    0.06
    ."));↵
    0.06
     microbial
    0.06
    кур
    0.06
    Act Density 0.006%

    No Known Activations