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

    Neuronpedia

    INDEX
    Explanations

    shown

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of numeric measurements or values—especially floating-point numbers—in the technical text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ляють
    -0.07
     jScrollPane
    -0.07
     endanger
    -0.07
    inář
    -0.06
     Müdür
    -0.06
     rebounds
    -0.06
    .Condition
    -0.06
     prayers
    -0.06
    屆
    -0.06
    icari
    -0.06
    POSITIVE LOGITS
    =length
    0.06
     rallying
    0.06
        
    0.06
     вет
    0.06
    /@
    0.06
    _exist
    0.06
    остат
    0.06
    Veter
    0.06
    etti
    0.06
    WARE
    0.06
    Act Density 0.010%

    No Known Activations