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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects numeric expressions and measurements (especially decimals and percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     कर
    -0.07
     wordt
    -0.07
     haar
    -0.07
    oxide
    -0.07
     playoffs
    -0.07
     Koh
    -0.07
     Peb
    -0.07
     Coil
    -0.06
    ��
    -0.06
     resistant
    -0.06
    POSITIVE LOGITS
    ="../../
    0.07
    ='',
    0.07
    .='
    0.07
    。（
    0.07
     máte
    0.06
     HEAP
    0.06
    .entrySet
    0.06
     fotograf
    0.06
     LI
    0.06
    وقع
    0.06
    Act Density 0.013%

    No Known Activations