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

    Neuronpedia

    INDEX
    Explanations

    velvet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ˘
    -0.08
    ItemAt
    -0.07
     yardımcı
    -0.07
    Ѳ
    -0.07
     spacious
    -0.07
    全日
    -0.07
    ᵗ
    -0.07
     exemp
    -0.06
    うち
    -0.06
    邨
    -0.06
    POSITIVE LOGITS
     vidéos
    0.08
     velvet
    0.08
    שרות
    0.07
    record
    0.07
    مر
    0.07
    ➤
    0.07
     directives
    0.07
     lớp
    0.07
     them
    0.07
     slapped
    0.07
    Act Density 0.001%

    No Known Activations