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

    Neuronpedia

    INDEX
    Explanations

    General purpose text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    考虑
    -0.07
    关于
    -0.07
     가정
    -0.06
    (graph
    -0.06
     jiný
    -0.06
     readings
    -0.06
     Levin
    -0.06
    окрема
    -0.06
     οποία
    -0.06
     Bose
    -0.06
    POSITIVE LOGITS
     πολυ
    0.08
     نف
    0.07
    (field
    0.06
    INV
    0.06
    _formula
    0.06
    emean
    0.06
     ine
    0.06
    운
    0.06
    越
    0.06
     erro
    0.06
    Act Density 0.042%

    No Known Activations