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

    Neuronpedia

    INDEX
    Explanations

    AI-enabled monitoring and detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertino
    -0.07
     Ross
    -0.07
     Murder
    -0.06
    _wc
    -0.06
     Barth
    -0.06
     elseif
    -0.06
    emales
    -0.06
     nonsense
    -0.06
    zo
    -0.06
     Automatically
    -0.06
    POSITIVE LOGITS
     Outdoor
    0.06
    .parametrize
    0.06
    Twig
    0.06
    ораль
    0.06
    .currentTarget
    0.06
    .SwingConstants
    0.05
    ::_('
    0.05
    _feedback
    0.05
    Anchor
    0.05
    )?↵
    0.05
    Act Density 0.391%

    No Known Activations