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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =[
    -0.07
     mascot
    -0.07
    .token
    -0.07
    allo
    -0.06
    Hat
    -0.06
     viewport
    -0.06
     sap
    -0.06
     dpi
    -0.06
    -fetch
    -0.06
     oslo
    -0.06
    POSITIVE LOGITS
    亭
    0.07
     sẵn
    0.06
    Prediction
    0.06
     our
    0.06
    ayette
    0.06
    icaret
    0.06
     مانند
    0.06
     مهم
    0.06
     Adams
    0.06
    ایش
    0.06
    Act Density 0.007%

    No Known Activations