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

    Neuronpedia

    INDEX
    Explanations

    divorce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     말
    -0.07
    asive
    -0.07
    -New
    -0.06
     Principles
    -0.06
    Programming
    -0.06
     Dann
    -0.06
    aval
    -0.06
     mathematics
    -0.06
    /XML
    -0.06
     اصول
    -0.06
    POSITIVE LOGITS
     almond
    0.06
     NEG
    0.06
                
    0.06
    Ố
    0.06
    .
↵↵
    0.06
     #"
    0.06
    unch
    0.06
    ưởng
    0.06
    .instances
    0.06
    elite
    0.06
    Act Density 0.089%

    No Known Activations