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

    Neuronpedia

    INDEX
    Explanations

    suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ابتدا
    -0.07
    Database
    -0.07
    よね
    -0.07
    students
    -0.06
     Materials
    -0.06
    .mongodb
    -0.06
     Lorem
    -0.06
     studs
    -0.06
     male
    -0.06
    ild
    -0.06
    POSITIVE LOGITS
     اله
    0.07
     مط
    0.06
     هش
    0.06
    iggins
    0.06
    une
    0.06
    }"↵↵
    0.06
    ichte
    0.06
    ento
    0.06
    ());
    0.06
    рукт
    0.06
    Act Density 0.075%

    No Known Activations