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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onica
    -0.07
    (hour
    -0.07
    Iteration
    -0.07
    (fixture
    -0.06
     Ku
    -0.06
     áreas
    -0.06
    _nodes
    -0.06
    gambar
    -0.06
    cow
    -0.06
    getList
    -0.06
    POSITIVE LOGITS
    メント
    0.06
     أخرى
    0.06
     دارند
    0.06
    تين
    0.06
    _vel
    0.06
    pq
    0.06
     sturdy
    0.06
     تک
    0.06
    chen
    0.06
     있고
    0.06
    Act Density 0.003%

    No Known Activations