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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens, in particular the numeral “50.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ิต
    -0.07
    计算
    -0.07
    кул
    -0.07
    амет
    -0.06
    兴
    -0.06
    903
    -0.06
    573
    -0.06
    Entered
    -0.06
    巡
    -0.06
    ческих
    -0.06
    POSITIVE LOGITS
     univerz
    0.07
     designed
    0.07
    rell
    0.07
    ICH
    0.06
     그렇
    0.06
     specificity
    0.06
    рів
    0.06
     коли
    0.06
     aaa
    0.06
     balanced
    0.06
    Act Density 0.005%

    No Known Activations