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

    Neuronpedia

    INDEX
    Explanations

    up or down

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     денег
    -0.08
    _toggle
    -0.08
     bipolar
    -0.07
    줫
    -0.07
    _school
    -0.07
     princes
    -0.07
    宝贝
    -0.07
     continent
    -0.07
    -seat
    -0.07
     liste
    -0.06
    POSITIVE LOGITS
     отно
    0.07
     interest
    0.07
    iale
    0.07
    Ί
    0.07
    Answer
    0.07
    MORE
    0.07
    蒂
    0.07
    メ
    0.07
    과
    0.07
     adds
    0.07
    Act Density 0.012%

    No Known Activations