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

    Neuronpedia

    INDEX
    Explanations

    130

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Directories
    -0.07
     Δ
    -0.07
    ечение
    -0.07
    檢
    -0.06
     мл
    -0.06
     التس
    -0.06
     خواهد
    -0.06
     ksi
    -0.06
     broadcasts
    -0.06
     THAN
    -0.06
    POSITIVE LOGITS
    .ul
    0.07
    üny
    0.06
    afs
    0.06
    قيق
    0.06
     真
    0.06
     Practice
    0.06
     dagger
    0.06
    _bag
    0.06
     Kathy
    0.06
    IDO
    0.06
    Act Density 0.001%

    No Known Activations