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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ροι
    -0.07
     Near
    -0.07
     Commerce
    -0.06
    кет
    -0.06
    apor
    -0.06
    UND
    -0.06
     основном
    -0.06
     получения
    -0.06
    ैन
    -0.06
     опис
    -0.06
    POSITIVE LOGITS
     aft
    0.07
     styl
    0.07
     assort
    0.06
     atr
    0.06
     Xuân
    0.06
     mcc
    0.06
    IV
    0.06
     tumult
    0.06
     uch
    0.06
     hey
    0.06
    Act Density 0.019%

    No Known Activations