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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -centered
    -0.07
     alım
    -0.07
    -service
    -0.07
     Lorem
    -0.07
     Willi
    -0.07
    	connection
    -0.06
     thiểu
    -0.06
    UserRole
    -0.06
     shows
    -0.06
    ourced
    -0.06
    POSITIVE LOGITS
    /ac
    0.06
     inflation
    0.06
     Grain
    0.06
    мами
    0.06
     ζω
    0.06
     gerne
    0.06
     انتخابات
    0.06
    -number
    0.06
     unreal
    0.06
    _alpha
    0.06
    Act Density 0.209%

    No Known Activations