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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_max-act · gemini-2.0-flash

    The neuron fires on units of measurement (e.g. hours, litres, minutes) in conversion‐style expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     leases
    -0.07
    attach
    -0.06
     bufsize
    -0.06
    cn
    -0.06
    arten
    -0.06
     �
    -0.06
    uve
    -0.06
    igy
    -0.06
    amen
    -0.06
     mín
    -0.06
    POSITIVE LOGITS
    塞
    0.07
    �
    0.07
     gost
    0.06
     yarn
    0.06
     民
    0.06
     allele
    0.06
     Pre
    0.06
     Scientists
    0.06
     yaz
    0.06
     `(
    0.06
    Act Density 0.005%

    No Known Activations