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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oret
    -0.07
     ignorance
    -0.06
    vert
    -0.06
    _De
    -0.06
     Slam
    -0.06
    -Time
    -0.06
     detta
    -0.06
     dere
    -0.06
     sunset
    -0.06
     foll
    -0.06
    POSITIVE LOGITS
    ево
    0.06
    dir
    0.06
     جامعة
    0.06
    HomeAsUp
    0.06
    atee
    0.06
     А
    0.06
    HashTable
    0.06
     civilizations
    0.06
    students
    0.06
    .collection
    0.06
    Act Density 0.004%

    No Known Activations