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

    Neuronpedia

    INDEX
    Explanations

    Ordinal numbers

    np_max-act · gemini-2.0-flash

    The neuron detects ordinal time expressions (numbers with “th,” “nd,” etc.) indicating days or time points in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _MODE
    -0.07
     fread
    -0.06
    ENCHMARK
    -0.06
    riteria
    -0.06
    Credentials
    -0.06
     سب
    -0.06
    .Imaging
    -0.06
    оя
    -0.06
    _Class
    -0.06
    _allocation
    -0.05
    POSITIVE LOGITS
    lun
    0.07
    νηση
    0.07
     �
    0.06
    創
    0.06
    จากการ
    0.06
    Enjoy
    0.06
    +r
    0.06
    _:
    0.06
    ATHER
    0.06
    omi
    0.06
    Act Density 0.020%

    No Known Activations