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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yrs
    -0.06
    -query
    -0.06
    례
    -0.06
     mej
    -0.06
    Python
    -0.06
    裡
    -0.06
    acute
    -0.06
    ,key
    -0.06
    	Response
    -0.06
    دى
    -0.06
    POSITIVE LOGITS
    .CV
    0.07
    IMARY
    0.06
     successfully
    0.06
     vigorously
    0.06
     york
    0.06
    )++;↵
    0.06
    visející
    0.06
     شهری
    0.06
    ูน
    0.06
     TCHAR
    0.06
    Act Density 0.030%

    No Known Activations