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

    Neuronpedia

    INDEX
    Explanations

    Вот

    np_max-act · gemini-2.0-flash

    This neuron detects the Russian discourse marker “вот” used to introduce examples or items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fus
    -0.07
     Gew
    -0.06
    řez
    -0.06
     fais
    -0.06
    ládání
    -0.06
    eld
    -0.06
     महत
    -0.06
     humming
    -0.06
     lou
    -0.06
     lean
    -0.06
    POSITIVE LOGITS
    ToShow
    0.07
    WebpackPlugin
    0.07
     marginTop
    0.07
    Ngh
    0.07
    CID
    0.06
    .divide
    0.06
    CENT
    0.06
     semiclass
    0.06
     Vo
    0.06
    -----------↵↵
    0.06
    Act Density 0.005%

    No Known Activations