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

    Neuronpedia

    INDEX
    Explanations

    -C

    np_max-act · gemini-2.0-flash

    The neuron activates on the metadata header lines (e.g. Project-Id-Version, Report-MSGid-Bugs-To, POT-Creation-Date, PO-Revision-Date, etc.) in gettext .po translation files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
     collected
    -0.07
    client
    -0.07
    -xl
    -0.07
     Cloth
    -0.07
    Emoji
    -0.07
     Guill
    -0.06
     Persian
    -0.06
    出去
    -0.06
     James
    -0.06
    POSITIVE LOGITS
     نگهداری
    0.07
     endangered
    0.06
     přístup
    0.06
    ximo
    0.06
     {});↵↵
    0.06
     unconditional
    0.06
     msec
    0.06
     pracovní
    0.06
    enerated
    0.06
     attributes
    0.06
    Act Density 0.018%

    No Known Activations