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

    Neuronpedia

    INDEX
    Explanations

    зап

    np_max-act · gemini-2.0-flash

    The neuron detects Cyrillic-script text (i.e. fragments of Russian words).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     trois
    -0.07
     бес
    -0.07
     honour
    -0.07
     productId
    -0.07
     passe
    -0.06
    Img
    -0.06
     гро
    -0.06
     tostring
    -0.06
     fec
    -0.06
    附
    -0.06
    POSITIVE LOGITS
    ATS
    0.08
     зап
    0.07
     widely
    0.07
    Зап
    0.06
    EMP
    0.06
     West
    0.06
    .sel
    0.06
    .launch
    0.06
    Ws
    0.06
    ISTR
    0.06
    Act Density 0.009%

    No Known Activations