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

    Neuronpedia

    INDEX
    Explanations

    seem appear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breeding
    -0.07
     Spor
    -0.06
    241
    -0.06
     entityManager
    -0.06
    第四
    -0.06
    /footer
    -0.06
    protocols
    -0.06
     همان
    -0.06
    reads
    -0.06
     predictions
    -0.06
    POSITIVE LOGITS
     truly
    0.06
    \Twig
    0.06
     deeply
    0.06
    _globals
    0.06
    _done
    0.06
     Inject
    0.06
    优
    0.06
     missed
    0.06
     tvá
    0.06
    措
    0.06
    Act Density 0.021%

    No Known Activations