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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect technical acronyms and abbreviations referring to LTE (Long Term Evolution) network elements and related cellular‐network components.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     entertained
    -0.08
    HV
    -0.07
     caffeine
    -0.07
    ą
    -0.07
     skutečně
    -0.07
    (search
    -0.07
    YE
    -0.07
    respect
    -0.06
     whence
    -0.06
     Cleanup
    -0.06
    POSITIVE LOGITS
     Phân
    0.08
    '),
↵
    0.06
    _PICTURE
    0.06
     ソ
    0.06
    _decimal
    0.06
     CDN
    0.06
     آموزش
    0.06
     sage
    0.06
    Lesson
    0.06
    ()");↵
    0.06
    Act Density 0.005%

    No Known Activations