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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing decimal points (i.e., floating-point measurements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     giá
    -0.07
     імені
    -0.06
    
    -0.06
     voluntary
    -0.06
     imposed
    -0.06
     cat
    -0.06
     ontvangst
    -0.06
    预
    -0.06
    .Inv
    -0.06
     congrat
    -0.05
    POSITIVE LOGITS
     поки
    0.07
     dù
    0.07
    upo
    0.06
    _ASSUME
    0.06
    Language
    0.06
    sdale
    0.06
    terior
    0.06
     ErrorHandler
    0.06
    Increase
    0.06
     Datum
    0.06
    Act Density 0.033%

    No Known Activations