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

    Neuronpedia

    INDEX
    Explanations

    GNU General Public License

    np_max-act · gemini-2.0-flash

    The neuron fires on decimal numeric literals (floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    @
    -0.08
     دیده
    -0.07
    @c
    -0.07
    _NOT
    -0.07
    ふ
    -0.07
     Wisdom
    -0.07
    SID
    -0.07
    }}">{{$
    -0.07
    بد
    -0.07
     zug
    -0.07
    POSITIVE LOGITS
    vect
    0.07
     requirement
    0.07
    _matched
    0.06
     temporary
    0.06
     aligned
    0.06
     dụng
    0.06
     devastated
    0.06
    าศ
    0.06
    icial
    0.06
     ConcurrentHashMap
    0.06
    Act Density 0.001%

    No Known Activations