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

    Neuronpedia

    INDEX
    Explanations

    Numbers and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Summary
    -0.06
    Times
    -0.06
    _blocks
    -0.06
    _population
    -0.06
    افة
    -0.06
    ，然后
    -0.06
    itored
    -0.06
     sweaty
    -0.06
    osed
    -0.06
    employees
    -0.06
    POSITIVE LOGITS
     Vend
    0.07
    %↵↵
    0.06
    .compile
    0.06
    .Views
    0.06
     Revised
    0.06
    ...↵
    0.06
     stddev
    0.06
    ...↵↵
    0.06
     kell
    0.06
     관
    0.06
    Act Density 0.001%

    No Known Activations