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

    Neuronpedia

    INDEX
    Explanations

    linguistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (image
    -0.08
    _UPLOAD
    -0.08
     scanned
    -0.08
    מונה
    -0.08
     ор
    -0.08
    scan
    -0.08
     syllabus
    -0.08
    mainder
    -0.07
    .scan
    -0.07
     মার্চ
    -0.07
    POSITIVE LOGITS
     etiquette
    0.14
     polite
    0.14
     courteous
    0.14
     politely
    0.13
     respectful
    0.13
     polit
    0.12
     greetings
    0.11
     respectfully
    0.11
    敬
    0.11
     höf
    0.10
    Act Density 0.018%

    No Known Activations