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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     жар
    -0.07
    _ROOM
    -0.06
     Pill
    -0.06
    dan
    -0.06
     Room
    -0.06
     gå
    -0.06
     продукції
    -0.06
    (Mock
    -0.06
     вст
    -0.06
     ith
    -0.06
    POSITIVE LOGITS
    heritance
    0.07
     aggreg
    0.06
    nici
    0.06
    833
    0.06
     Used
    0.06
    Cour
    0.06
    歡
    0.06
     работа
    0.06
     friendships
    0.06
    _reason
    0.06
    Act Density 0.020%

    No Known Activations