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

    Neuronpedia

    INDEX
    Explanations

    notebook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sendMessage
    -0.07
     metal
    -0.07
    .init
    -0.06
     mph
    -0.06
    -states
    -0.06
     intolerance
    -0.06
    �
    -0.06
     vlády
    -0.06
    \xaa
    -0.06
     ما
    -0.06
    POSITIVE LOGITS
     Notebook
    0.08
     withholding
    0.07
    _TEM
    0.06
    ैल
    0.06
     nab
    0.06
    豪
    0.06
    Major
    0.06
    IVES
    0.06
     Detect
    0.06
    (pts
    0.06
    Act Density 0.003%

    No Known Activations