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

    Neuronpedia

    INDEX
    Explanations

    partitioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     full
    -0.08
     onboard
    -0.08
     att
    -0.08
     optionally
    -0.07
    -contained
    -0.07
     if
    -0.07
    insic
    -0.07
    -0.07
    12
    -0.07
     potentially
    -0.07
    POSITIVE LOGITS
     تقس
    0.17
     تقسیم
    0.16
    划
    0.15
    แบ่ง
    0.14
     распредел
    0.14
     dağı
    0.14
    .partition
    0.14
     divisão
    0.14
     ভাগ
    0.13
     distribuição
    0.13
    Act Density 0.024%
    No Known Activations