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

    Neuronpedia

    INDEX
    Explanations

    Japanese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     females
    -0.06
    Col
    -0.06
     hại
    -0.06
    >>)
    -0.06
     services
    -0.06
    exao
    -0.06
     将
    -0.06
     vyt
    -0.06
     worry
    -0.05
    	number
    -0.05
    POSITIVE LOGITS
     Fuji
    0.07
    午
    0.07
     پیش
    0.06
     علی
    0.06
     Approved
    0.06
     ::::::::
    0.06
     downstairs
    0.06
     hóa
    0.06
     rowIndex
    0.06
    شن
    0.06
    Act Density 0.014%

    No Known Activations