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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giảng
    -0.06
    phem
    -0.06
     livro
    -0.06
    陷
    -0.06
     παν
    -0.05
    iles
    -0.05
     identifiers
    -0.05
    �
    -0.05
    什么
    -0.05
    万
    -0.05
    POSITIVE LOGITS
    .Event
    0.07
    ��加
    0.07
    .Car
    0.07
     since
    0.07
    .Millisecond
    0.07
     grac
    0.07
    \<^
    0.07
    ,request
    0.07
    _matrix
    0.07
    <Key
    0.07
    Act Density 0.035%

    No Known Activations