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

    Neuronpedia

    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash

    stories involving unconventional relationships or dynamics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron remains inactive and does not respond to any meaningful token pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .pa
    -0.07
     andere
    -0.07
    _old
    -0.07
     الناس
    -0.06
     kommer
    -0.06
    umont
    -0.06
     хоч
    -0.06
    _background
    -0.06
    _hor
    -0.06
    .pk
    -0.06
    POSITIVE LOGITS
    Res
    0.07
     sucks
    0.06
    례
    0.06
     terminates
    0.06
    іблі
    0.06
     toArray
    0.06
    .twig
    0.06
    <Vec
    0.06
    osy
    0.06
    (send
    0.06
    Act Density 0.058%

    No Known Activations