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

    Neuronpedia

    INDEX
    Explanations

    sorting numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (digits, signs, decimal points, and fractions), i.e. it detects numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    esture
    -0.06
     remembers
    -0.06
     pas
    -0.06
    IMP
    -0.06
     шлях
    -0.06
     rend
    -0.06
    66
    -0.06
    px
    -0.06
    ippi
    -0.06
    _Dep
    -0.06
    POSITIVE LOGITS
     iets
    0.07
    ."));↵
    0.06
     siyaset
    0.06
    tics
    0.06
     Лі
    0.06
    $res
    0.06
    	se
    0.06
     Flow
    0.06
    _nt
    0.06
    '};↵
    0.06
    Act Density 0.007%

    No Known Activations