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

    Neuronpedia

    INDEX
    Explanations

    scientific abbreviations/references

    np_max-act · gemini-2.0-flash

    This neuron detects uppercase initialisms or acronyms (sequences of capital letters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    869
    -0.07
    Ａ
    -0.06
    575
    -0.06
    371
    -0.06
    611
    -0.06
     Sesso
    -0.06
    +')
    -0.06
    ุทธ
    -0.06
    ЛЬ
    -0.05
     theatrical
    -0.05
    POSITIVE LOGITS
     проведення
    0.07
    PT
    0.06
     Equal
    0.06
    outed
    0.06
    pedo
    0.06
     MI
    0.06
     tabi
    0.06
    blo
    0.06
     cravings
    0.06
    ducers
    0.06
    Act Density 0.233%

    No Known Activations